usage limit still consumed after request has been blocked by security classifier

What version of Codex CLI is running?

codex-cli 0.153.4

What subscription do you have?

Plus

Which model were you using?

gpt-5.6-sol medium

What platform is your computer?

Linux 7.2.4-arch1-2 x86_64 unknown

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

xfce4-terminal

Codex doctor report

{
  "schemaVersion": 1,
  "generatedAt": "1789210287s since unix epoch",
  "overallStatus": "ok",
  "codexVersion": "0.153.4",
  "checks": {
    "app_server.status": {
      "id": "app_server.status",
      "category": "app-server",
      "status": "ok",
      "summary": "background server is not running",
      "details": {
        "control socket": "/home/sev/.codex/app-server-control/app-server-control.sock",
        "daemon state dir": "/home/sev/.codex/app-server-daemon",
        "mode": "ephemeral",
        "pid file": "/home/sev/.codex/app-server-daemon/app-server.pid (missing)",
        "settings": "/home/sev/.codex/app-server-daemon/settings.json (missing)",
        "status": "not running",
        "update-loop pid file": "/home/sev/.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": "/home/sev/.codex/auth.json",
        "auth storage mode": "File",
        "stored API key": "false",
        "stored ChatGPT tokens": "true",
        "stored agent identity": "false",
        "stored auth mode": "chatgpt"
      },
      "remediation": null,
      "durationMs": 0
    },
    "config.load": {
      "id": "config.load",
      "category": "config",
      "status": "ok",
      "summary": "config loaded",
      "details": {
        "CODEX_HOME": "/home/sev/.codex",
        "config.toml": "/home/sev/.codex/config.toml",
        "config.toml parse": "ok",
        "cwd": "/home/sev",
        "enabled feature flags": "shell_tool, view_image, sleep_tool, unified_exec, unified_exec_zsh_fork, shell_snapshot, content_item_kinds, code_mode_host, terminal_resize_reflow, sqlite, memories, hooks, enable_request_compression, unbounded_connection_retries, multi_agent, apps, tool_search_always_defer_mcp_tools, tool_suggest, plugins, in_app_browser, in_app_chat, in_app_dictation, in_app_local_automation, in_app_updates, browser_use, browser_use_full_cdp_access, browser_use_external, computer_use, remote_plugin, plugin_sharing, image_generation, resize_all_images, item_ids, skill_mcp_dependency_install, skill_search, mentions_v2, steer, guardian_approval, goals, collaboration_modes, tool_call_mcp_elicitation, auth_elicitation, personality, fast_mode, tui_app_server, remote_compaction_v2, compaction_image_budget, workspace_dependencies",
        "feature flag overrides": "memories=true",
        "feature flags enabled": "48",
        "log dir": "/home/sev/.codex/log",
        "mcp servers": "0",
        "model": "gpt-5.6-sol",
        "model provider": "openai",
        "sqlite home": "/home/sev/.codex"
      },
      "remediation": null,
      "durationMs": 0
    },
    "git.environment": {
      "id": "git.environment",
      "category": "git",
      "status": "ok",
      "summary": "git version 2.55.0",
      "details": {
        "PATH git #1": "/usr/bin/git",
        "PATH git #2": "/bin/git",
        "PATH git entries": "2",
        "git build options": "git version 2.55.0; cpu: x86_64; built from commit: e9019fcafe0040228b8631c30f97ae1adb61bcdc; sizeof-long: 8; sizeof-size_t: 8; shell-path: /bin/sh; rust: enabled; feature: fsmonitor--daemon; gettext: enabled; libcurl: 8.21.0; OpenSSL: OpenSSL 3.6.3 9 Jun 2026; zlib-ng: 2.3.3; SHA-1: SHA1_DC; SHA-256: SHA256_BLK; default-ref-format: files; default-hash: sha1",
        "git exec path": "/usr/lib/git-core",
        "git version": "git version 2.55.0",
        "repo detected": "false",
        "selected git": "/usr/bin/git"
      },
      "remediation": null,
      "durationMs": 13
    },
    "installation": {
      "id": "installation",
      "category": "install",
      "status": "ok",
      "summary": "installation looks consistent",
      "details": {
        "PATH codex #1": "/usr/bin/codex",
        "PATH codex #2": "/bin/codex",
        "PATH codex entries": "2",
        "current executable": "/usr/bin/codex",
        "install context": "other",
        "managed by Vite+": "false",
        "managed by bun": "false",
        "managed by npm": "false",
        "managed by pnpm": "false",
        "managed package root": "not set"
      },
      "remediation": null,
      "durationMs": 0
    },
    "mcp.config": {
      "id": "mcp.config",
      "category": "mcp",
      "status": "ok",
      "summary": "no MCP servers configured",
      "details": {},
      "remediation": null,
      "durationMs": 0
    },
    "network.env": {
      "id": "network.env",
      "category": "network",
      "status": "ok",
      "summary": "network-related environment looks readable",
      "details": {
        "managed proxy": "not configured",
        "proxy env vars": "none",
        "respect system proxy": "disabled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "network.provider_reachability": {
      "id": "network.provider_reachability",
      "category": "reachability",
      "status": "ok",
      "summary": "active provider endpoints are reachable over HTTP",
      "details": {
        "ChatGPT inference URL": "https://chatgpt.com/backend-api/<redacted> reachable (HTTP 405)",
        "reachability mode": "ChatGPT auth"
      },
      "remediation": null,
      "durationMs": 209
    },
    "network.websocket_reachability": {
      "id": "network.websocket_reachability",
      "category": "websocket",
      "status": "ok",
      "summary": "Responses WebSocket handshake succeeded",
      "details": {
        "DNS": "2 IPv4, 2 IPv6, first IPv6",
        "auth mode": "chatgpt",
        "connect timeout": "15000 ms",
        "endpoint": "wss://chatgpt.com/backend-api/<redacted>",
        "handshake result": "HTTP 101 Switching Protocols",
        "model provider": "openai",
        "provider name": "OpenAI",
        "proxy env vars": "none",
        "reasoning header": "false",
        "server model present": "false",
        "supports websockets": "true",
        "wire API": "responses"
      },
      "remediation": null,
      "durationMs": 779
    },
    "runtime.provenance": {
      "id": "runtime.provenance",
      "category": "runtime",
      "status": "ok",
      "summary": "running local build on linux-x86_64",
      "details": {
        "commit": "unknown",
        "current executable": "/usr/bin/codex",
        "install method": "other",
        "platform": "linux-x86_64",
        "version": "0.153.4"
      },
      "remediation": null,
      "durationMs": 0
    },
    "runtime.search": {
      "id": "runtime.search",
      "category": "search",
      "status": "ok",
      "summary": "search is OK (system)",
      "details": {
        "search command": "rg",
        "search command readiness": "ripgrep 15.2.0",
        "search provider": "system"
      },
      "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": "/home/sev/.codex/tmp/arg0/codex-arg0VQ4h63/codex-linux-sandbox",
        "execve wrapper helper": "/home/sev/.codex/tmp/arg0/codex-arg0VQ4h63/codex-execve-wrapper",
        "filesystem sandbox": "restricted",
        "network sandbox": "restricted"
      },
      "remediation": null,
      "durationMs": 0
    },
    "security.endpoint": {
      "id": "security.endpoint",
      "category": "security",
      "status": "ok",
      "summary": "endpoint protection is not inspected on this platform",
      "details": {
        "endpoint products": "not inspected on this platform"
      },
      "remediation": null,
      "durationMs": 0
    },
    "state.paths": {
      "id": "state.paths",
      "category": "state",
      "status": "ok",
      "summary": "state paths and databases are inspectable",
      "details": {
        "CODEX_HOME": "/home/sev/.codex (dir)",
        "active rollout files": "125 files, 344494189 total bytes, 2755953 average bytes",
        "archived rollout files": "0 files, 0 total bytes, 0 average bytes",
        "goals DB": "/home/sev/.codex/goals_1.sqlite (file)",
        "goals DB integrity": "ok",
        "log DB": "/home/sev/.codex/logs_2.sqlite (file)",
        "log DB integrity": "ok",
        "log dir": "/home/sev/.codex/log (dir)",
        "memories DB": "/home/sev/.codex/memories_1.sqlite (file)",
        "memories DB integrity": "ok",
        "queue DB": "/home/sev/.codex/queue_1.sqlite (file)",
        "queue DB integrity": "ok",
        "sqlite home": "/home/sev/.codex (dir)",
        "state DB": "/home/sev/.codex/state_5.sqlite (file)",
        "state DB integrity": "ok",
        "thread history DB": "/home/sev/.codex/thread_history_1.sqlite (file)",
        "thread history DB integrity": "ok"
      },
      "remediation": null,
      "durationMs": 108
    },
    "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",
        "rollout DB active files": "125",
        "rollout DB active rows": "125",
        "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=125",
        "rollout DB rows": "125",
        "rollout DB scan cap reached": "false",
        "rollout DB scan errors": "0",
        "rollout DB sources": "cli=84, subagent:thread_spawn=36, subagent:other=5",
        "rollout DB stale rows": "0"
      },
      "remediation": null,
      "durationMs": 28
    },
    "system.disk": {
      "id": "system.disk",
      "category": "disk",
      "status": "ok",
      "summary": "sufficient free disk space (131.1 GiB)",
      "details": {
        "CODEX_HOME available": "131.1 GiB",
        "failure threshold": "1.0 GiB",
        "warning threshold": "5.0 GiB",
        "worktree available": "131.1 GiB"
      },
      "remediation": null,
      "durationMs": 0
    },
    "system.environment": {
      "id": "system.environment",
      "category": "system",
      "status": "ok",
      "summary": "OS language en-US",
      "details": {
        "EDITOR": "set",
        "LANG": "en_US.UTF-8",
        "LESS": "set",
        "PAGER": "set",
        "VISUAL": "not set",
        "os": "EndeavourOS Rolling Release (rolling) [64-bit]",
        "os language": "en-US",
        "os type": "EndeavourOS",
        "os version": "Rolling Release"
      },
      "remediation": null,
      "durationMs": 6
    },
    "terminal.env": {
      "id": "terminal.env",
      "category": "terminal",
      "status": "ok",
      "summary": "terminal metadata was detected",
      "details": {
        "COLORTERM": "truecolor",
        "DISPLAY": "present",
        "color output": "disabled (stdout is not a terminal)",
        "effective locale": "en_US.UTF-8",
        "stderr is terminal": "true",
        "stdin is terminal": "true",
        "stdout is terminal": "false",
        "terminal": "VTE",
        "terminal size": "209x49",
        "terminal version": "8401"
      },
      "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": "sev",
        "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": "0.154.0",
        "check for update on startup": "true",
        "last checked at": "2026-09-11T17:54:37.166325068Z",
        "latest version": "0.154.0",
        "latest version status": "newer version is available",
        "update action": "manual or unknown",
        "version cache": "/home/sev/.codex/version.json"
      },
      "remediation": null,
      "durationMs": 192
    }
  }
}

What issue are you seeing?

I hit a security classifier block, but usage limit was still consumed without any input from me or content shown (25% warning -> block -> 10% warning -> 5% warning).
See attached screenshot or transcribed screenshot content from below.

While blocking a (harmless) request is already annoying, then also using up the remaining usage, so I can't even retry with another model, seems not ideal. Especially considering this was not even the flagship model.

Screenshot transcription:

• Explored
  └ Search NewTokenEmpty|NewConnectionIdInvalid|oneRttOptAck|oneRttUnxpFrType|quicKeyUpdat

⚠ Heads up, you have less than 25% of your 5h limit left. Run /status for a breakdown.

🛈 This content can't be shown
  We take extra caution with cybersecurity requests. If you're a security professional, yo
  Trusted Access: https://chatgpt.com/cyber/
  Learn more: https://help.openai.com/en/articles/20001326

⚠ Heads up, you have less than 10% of your 5h limit left. Run /status for a breakdown.

⚠ Heads up, you have less than 5% of your 5h limit left. Run /status for a breakdown.

• Feedback uploaded. Please open an issue using the following URL:

  https://github.com/openai/codex/issues/new?template=3-cli.yml&steps=Uploaded%20thread:%2

  Or mention your thread ID 01a09523-71f1-7283-b7b5-f3c94ecaa097 in an existing issue.

• Feedback uploaded. Please open an issue using the following URL:

  https://github.com/openai/codex/issues/new?template=3-cli.yml&steps=Uploaded%20thread:%2

  Or mention your thread ID 01a09523-71f1-7283-b7b5-f3c94ecaa097 in an existing issue.

› Ask Codex to do anything

gpt-5.6-sol medium · ~/projects/quicSML · main · Context 25% left · 5h 4% left · weekly

What steps can reproduce the bug?

Uploaded thread: 01a09523-71f1-7283-b7b5-f3c94ecaa097

What is the expected behavior?

1. To not block harmless requests in the first place
2. Don't use the usage limit if no results/content are provided
3. Ideally refund / don't count tokens used for requests/threads that are blocked. Not really my fault the security classifiers are not precise enough.

Additional information

No response

Reproduce the report with Codex CLI 0.153.4 by sending a request that the security classifier blocks, then trace how usage is recorded relative to that classification. Done means blocked requests do not consume the usage limit and a regression test covers the behavior.