Monthly usage limit drains abnormally fast (25% → 5% within ~15 tool calls in one session)

The report names no repository files, tests, or entry points. Start by reproducing the usage change with Codex CLI 0.144.5, gpt-5.5, and a Plus account while recording tool calls and remaining quota; done means identifying whether the client reports or triggers incorrect accounting and adding a regression test if a repository-side cause is found.

What version of Codex CLI is running?

codex-cli 0.144.5

What subscription do you have?

Plus

Which model were you using?

gpt-5.5 (medium reasoning)

What platform is your computer?

Darwin 24.6.0 arm64 arm

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

ZED

Codex doctor report

{
  "schemaVersion": 1,
  "generatedAt": "1784218627s since unix epoch",
  "overallStatus": "warning",
  "codexVersion": "0.144.5",
  "checks": {
    "app_server.status": {
      "id": "app_server.status",
      "category": "app-server",
      "status": "ok",
      "summary": "background server is not running",
      "details": {
        "control socket": "/Users/szymonnowicki/.codex/app-server-control/app-server-control.sock",
        "daemon state dir": "/Users/szymonnowicki/.codex/app-server-daemon",
        "mode": "ephemeral",
        "pid file": "/Users/szymonnowicki/.codex/app-server-daemon/app-server.pid (missing)",
        "settings": "/Users/szymonnowicki/.codex/app-server-daemon/settings.json (missing)",
        "status": "not running",
        "update-loop pid file": "/Users/szymonnowicki/.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 env vars present": "OPENAI_API_KEY",
        "auth file": "/Users/szymonnowicki/.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": "/Users/szymonnowicki/.codex",
        "config.toml": "/Users/szymonnowicki/.codex/config.toml",
        "config.toml parse": "ok",
        "cwd": "/Users/szymonnowicki/Local Sites/sklepledy/app/public/wp-content/themes/alufrost-shop",
        "enabled feature flags": "shell_tool, unified_exec, shell_snapshot, code_mode_host, 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, remote_plugin, plugin_sharing, image_generation, resize_all_images, skill_mcp_dependency_install, mentions_v2, steer, guardian_approval, goals, collaboration_modes, tool_call_mcp_elicitation, auth_elicitation, personality, fast_mode, tui_app_server, remote_compaction_v2, workspace_dependencies",
        "feature flag overrides": "none",
        "feature flags enabled": "35",
        "log dir": "/Users/szymonnowicki/.codex/log",
        "mcp servers": "1",
        "model": "gpt-5.5",
        "model provider": "openai",
        "sqlite home": "/Users/szymonnowicki/.codex"
      },
      "remediation": null,
      "durationMs": 0
    },
    "git.environment": {
      "id": "git.environment",
      "category": "git",
      "status": "ok",
      "summary": "git version 2.52.0",
      "details": {
        ".git entry": "directory",
        "PATH git #1": "/opt/homebrew/bin/git",
        "PATH git #2": "/usr/bin/git",
        "PATH git entries": "2",
        "git branch": "master",
        "git build options": "git version 2.52.0; cpu: arm64; no commit associated with this build; sizeof-long: 8; sizeof-size_t: 8; shell-path: /bin/sh; rust: disabled; feature: fsmonitor--daemon; libcurl: 8.7.1; zlib: 1.2.12; SHA-1: SHA1_DC; SHA-256: SHA256_BLK; default-ref-format: files; default-hash: sha1",
        "git exec path": "/opt/homebrew/opt/git/libexec/git-core",
        "git version": "git version 2.52.0",
        "repo detected": "true",
        "repo root": "/Users/szymonnowicki/Local Sites/sklepledy/app/public/wp-content/themes/alufrost-shop",
        "selected git": "/opt/homebrew/bin/git"
      },
      "remediation": null,
      "durationMs": 165
    },
    "installation": {
      "id": "installation",
      "category": "install",
      "status": "ok",
      "summary": "installation looks consistent",
      "details": {
        "PATH codex #1": "/opt/homebrew/bin/codex",
        "current executable": "/opt/homebrew/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin/codex",
        "install context": "npm (package /opt/homebrew/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin, bin /opt/homebrew/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin, resources /opt/homebrew/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-resources, path /opt/homebrew/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 by pnpm": "false",
        "managed package root": "/opt/homebrew/lib/node_modules/@openai/codex",
        "npm update target": "/opt/homebrew/lib/node_modules/@openai/codex"
      },
      "remediation": null,
      "durationMs": 167
    },
    "mcp.config": {
      "id": "mcp.config",
      "category": "mcp",
      "status": "warning",
      "summary": "MCP configuration has optional issues",
      "details": {
        "configured servers": "1",
        "disabled servers": "0",
        "pencil": "stdio command \"/Applications/Pencil.app/Contents/Resources/app.asar.unpacked/out/mcp-server-darwin-arm64\" is not resolvable (No such file or directory (os error 2))",
        "stdio servers": "1"
      },
      "remediation": "Set the missing MCP env vars or disable the affected server.",
      "durationMs": 0
    },
    "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 API base URL": "https://api.openai.com/v1 reachable (HTTP 404)",
        "openai API route probe": "https://api.openai.com/v1/<redacted> route exists (HTTP 401)",
        "reachability mode": "API key auth"
      },
      "remediation": null,
      "durationMs": 914
    },
    "network.websocket_reachability": {
      "id": "network.websocket_reachability",
      "category": "websocket",
      "status": "ok",
      "summary": "Responses WebSocket handshake succeeded",
      "details": {
        "DNS": "2 IPv4, 0 IPv6, first IPv4",
        "auth mode": "chatgpt",
        "connect timeout": "15000 ms",
        "endpoint": "wss://chatgpt.com/backend-api/<redacted>",
        "handshake result": "HTTP 101 Switching Protocols",
        "model provider": "openai",
        "models etag present": "true",
        "provider name": "OpenAI",
        "proxy env vars": "none",
        "reasoning header": "false",
        "server model present": "false",
        "supports websockets": "true",
        "wire API": "responses"
      },
      "remediation": null,
      "durationMs": 857
    },
    "runtime.provenance": {
      "id": "runtime.provenance",
      "category": "runtime",
      "status": "ok",
      "summary": "running npm on macos-aarch64",
      "details": {
        "commit": "unknown",
        "current executable": "/opt/homebrew/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin/codex",
        "install method": "npm (package /opt/homebrew/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin, bin /opt/homebrew/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin, resources /opt/homebrew/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-resources, path /opt/homebrew/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path)",
        "platform": "macos-aarch64",
        "version": "0.144.5"
      },
      "remediation": null,
      "durationMs": 0
    },
    "runtime.search": {
      "id": "runtime.search",
      "category": "search",
      "status": "ok",
      "summary": "search is OK (bundled)",
      "details": {
        "search command": "/opt/homebrew/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/szymonnowicki/.codex/tmp/arg0/codex-arg0c5E1fb/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/szymonnowicki/.codex (dir)",
        "active rollout files": "2402 files, 153024721 total bytes, 63707 average bytes",
        "archived rollout files": "0 files, 0 total bytes, 0 average bytes",
        "goals DB": "/Users/szymonnowicki/.codex/goals_1.sqlite (file)",
        "goals DB integrity": "ok",
        "log DB": "/Users/szymonnowicki/.codex/logs_2.sqlite (file)",
        "log DB integrity": "ok",
        "log dir": "/Users/szymonnowicki/.codex/log (dir)",
        "memories DB": "/Users/szymonnowicki/.codex/memories_1.sqlite (file)",
        "memories DB integrity": "ok",
        "sqlite home": "/Users/szymonnowicki/.codex (dir)",
        "state DB": "/Users/szymonnowicki/.codex/state_5.sqlite (file)",
        "state DB integrity": "ok"
      },
      "remediation": null,
      "durationMs": 2853
    },
    "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": "2402",
        "rollout DB active rows": "2402",
        "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=2402",
        "rollout DB rows": "2402",
        "rollout DB scan cap reached": "false",
        "rollout DB scan errors": "0",
        "rollout DB sources": "exec=2265, cli=136, vscode=1",
        "rollout DB stale rows": "0"
      },
      "remediation": null,
      "durationMs": 3103
    },
    "system.environment": {
      "id": "system.environment",
      "category": "system",
      "status": "ok",
      "summary": "OS language pl-PL",
      "details": {
        "EDITOR": "not set",
        "LANG": "en_US.UTF-8",
        "VISUAL": "not set",
        "os": "Mac OS 15.6.1 [64-bit]",
        "os language": "pl-PL",
        "os type": "Mac OS",
        "os version": "15.6.1"
      },
      "remediation": null,
      "durationMs": 6
    },
    "terminal.env": {
      "id": "terminal.env",
      "category": "terminal",
      "status": "ok",
      "summary": "terminal metadata was detected",
      "details": {
        "COLORTERM": "truecolor",
        "TERM_PROGRAM": "zed",
        "color output": "enabled",
        "effective locale": "en_US.UTF-8",
        "stderr is terminal": "true",
        "stdin is terminal": "true",
        "stdout is terminal": "true",
        "terminal": "unknown",
        "terminal size": "90x29",
        "terminal version": "1.10.3+stable.324.0c54c414d522234de7298039708ffe85a116892a"
      },
      "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": "git repo root",
        "terminal title project value": "alufrost-shop",
        "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": "0.144.5",
        "check for update on startup": "true",
        "dismissed version": "0.140.0",
        "last checked at": "2026-07-16T05:39:16.971881Z",
        "latest version": "0.144.5",
        "latest version status": "current version is not older",
        "npm update target": "/opt/homebrew/lib/node_modules/@openai/codex",
        "update action": "npm install -g @openai/codex",
        "version cache": "/Users/szymonnowicki/.codex/version.json"
      },
      "remediation": null,
      "durationMs": 672
    }
  }
}

What issue are you seeing?

Monthly token usage limit drained from 25% remaining to 5% remaining within a single working session, across roughly 15 tool calls (mostly Read/Search on existing files, no large file writes). No corresponding heavy task was run — the calls were standard file reads (Read on ProductController.php, archive-product.blade.php, ArchiveProductController.php, single-product.blade.php, SettingsShop.php, ajax.php, vite.config.js, etc.) in a WordPress/Bedrock/Sage theme repo.

Notably, this session was a resumed session after an earlier prompt was interrupted mid-run:

■ Conversation interrupted - tell the model what to do differently.

I re-sent the same prompt immediately after the interruption. It's possible the interrupted session's context/cache was not properly cleared and got double-counted when the same prompt was re-run, causing inflated token accounting.

For reference, the prior task in the same CLI session reported:

Token usage: total=188 124 input=172 050 (+ 3 523 328 cached) output=16 074 (reasoning 3074)

This is a very large cached-token count relative to the actual output, which raises the question of whether cached context is being over-counted against the monthly limit, especially across resumed/interrupted sessions.

I have never used more than ~50% of a single 5-hour window in normal use, so a monthly limit dropping this fast in one session is inconsistent with my typical usage pattern.

What steps can reproduce the bug?

1. Start a Codex CLI session, run a task to completion (e.g. editing CSS/blade files), note token usage report.
2. Start a new prompt in the same session.
3. Interrupt the conversation mid-run (Conversation interrupted).
4. Re-send the same prompt again without starting a fresh session.
5. Continue running standard Read/Search tool calls (reading existing repo files, no large edits).
6. Observe monthly usage limit banner dropping rapidly (25% → 10% → 5%) within a small number of read-only tool calls.

Thread/session id: 019f6b9c-a881-7ea1-add9-1da57a2c5d5e

What is the expected behavior?

Monthly usage limit should decrease proportionally to actual token consumption (input + output), and cached/resumed session context should not be double-counted after an interruption. Read-only exploration of a handful of moderately-sized files should not consume ~20% of a monthly quota in a single session.

Additional information

This matches patterns reported in other issues around the same period (e.g. #30918 — "Usage limits draining abnormally fast on Plus: 70% to 100% in about 6 minutes on July 2, 2026"), where OpenAI acknowledged a usage-accounting bug and shipped a fix on June 30, 2026, but users continued to report abnormal drains afterward. Happy to provide sanitized session logs if useful (redacting prompts/file contents).