wasting tokens with names and a list of tokens remaining
Open 💬 1 comment Opened Aug 10, 2026 by noslouch
What version of Codex CLI is running?
0.146.0
What subscription do you have?
pro lite
Which model were you using?
gpt-5.6-sol
What platform is your computer?
Darwin 25.5.0 arm64 arm
What terminal emulator and version are you using (if applicable)?
iTerm2/tmux
Codex doctor report
{
"schemaVersion": 1,
"generatedAt": "1786329445s since unix epoch",
"overallStatus": "fail",
"codexVersion": "0.146.0",
"checks": {
"app_server.status": {
"id": "app_server.status",
"category": "app-server",
"status": "ok",
"summary": "background server is not running",
"details": {
"control socket": "/Users/brianwhitton/.codex/app-server-control/app-server-control.sock",
"daemon state dir": "/Users/brianwhitton/.codex/app-server-daemon",
"mode": "ephemeral",
"pid file": "/Users/brianwhitton/.codex/app-server-daemon/app-server.pid (missing)",
"settings": "/Users/brianwhitton/.codex/app-server-daemon/settings.json (missing)",
"status": "not running",
"update-loop pid file": "/Users/brianwhitton/.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/brianwhitton/.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/brianwhitton/.codex",
"config.toml": "/Users/brianwhitton/.codex/config.toml",
"config.toml parse": "ok",
"cwd": "/Users/brianwhitton/src/tank3",
"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, 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, workspace_dependencies",
"feature flag overrides": "none",
"feature flags enabled": "38",
"log dir": "/Users/brianwhitton/.codex/log",
"mcp servers": "0",
"model": "gpt-5.6-sol",
"model provider": "openai",
"sqlite home": "/Users/brianwhitton/.codex"
},
"remediation": null,
"durationMs": 0
},
"git.environment": {
"id": "git.environment",
"category": "git",
"status": "ok",
"summary": "git version 2.50.1 (Apple Git-155)",
"details": {
".git entry": "directory",
"PATH git #1": "/usr/bin/git",
"PATH git entries": "1",
"git branch": "main",
"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": "/Applications/Xcode.app/Contents/Developer/usr/libexec/git-core",
"git version": "git version 2.50.1 (Apple Git-155)",
"repo detected": "true",
"repo root": "/Users/brianwhitton/src/tank3",
"selected git": "/usr/bin/git"
},
"remediation": null,
"durationMs": 10
},
"installation": {
"id": "installation",
"category": "install",
"status": "ok",
"summary": "installation looks consistent",
"details": {
"PATH codex #1": "/opt/homebrew/bin/codex",
"current executable": "/opt/homebrew/bin/codex",
"install context": "brew (package /opt/homebrew/Caskroom/codex/0.146.0, bin /opt/homebrew/Caskroom/codex/0.146.0/bin, resources /opt/homebrew/Caskroom/codex/0.146.0/codex-resources, path /opt/homebrew/Caskroom/codex/0.146.0/codex-path)",
"managed by bun": "false",
"managed by npm": "false",
"managed by pnpm": "false",
"managed package root": "not set"
},
"remediation": null,
"durationMs": 2
},
"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": {
"proxy env vars": "none"
},
"remediation": null,
"durationMs": 0
},
"network.provider_reachability": {
"id": "network.provider_reachability",
"category": "reachability",
"status": "fail",
"summary": "one or more required provider endpoints are unreachable over HTTP",
"details": {
"ChatGPT base URL": "https://chatgpt.com/backend-api/ request timed out (required)",
"reachability mode": "ChatGPT auth"
},
"remediation": "Check proxy, VPN, firewall, DNS, and custom CA configuration.",
"durationMs": 3001
},
"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": 5520
},
"runtime.provenance": {
"id": "runtime.provenance",
"category": "runtime",
"status": "ok",
"summary": "running brew on macos-aarch64",
"details": {
"commit": "unknown",
"current executable": "/opt/homebrew/bin/codex",
"install method": "brew (package /opt/homebrew/Caskroom/codex/0.146.0, bin /opt/homebrew/Caskroom/codex/0.146.0/bin, resources /opt/homebrew/Caskroom/codex/0.146.0/codex-resources, path /opt/homebrew/Caskroom/codex/0.146.0/codex-path)",
"platform": "macos-aarch64",
"version": "0.146.0"
},
"remediation": null,
"durationMs": 0
},
"runtime.search": {
"id": "runtime.search",
"category": "search",
"status": "ok",
"summary": "search is OK (bundled)",
"details": {
"search command": "/opt/homebrew/Caskroom/codex/0.146.0/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/brianwhitton/.codex/tmp/arg0/codex-arg0SYUCkQ/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/brianwhitton/.codex (dir)",
"active rollout files": "370 files, 1454821765 total bytes, 3931950 average bytes",
"archived rollout files": "0 files, 0 total bytes, 0 average bytes",
"goals DB": "/Users/brianwhitton/.codex/goals_1.sqlite (file)",
"goals DB integrity": "ok",
"log DB": "/Users/brianwhitton/.codex/logs_2.sqlite (file)",
"log DB integrity": "ok",
"log dir": "/Users/brianwhitton/.codex/log (dir)",
"memories DB": "/Users/brianwhitton/.codex/memories_1.sqlite (file)",
"memories DB integrity": "ok",
"sqlite home": "/Users/brianwhitton/.codex (dir)",
"state DB": "/Users/brianwhitton/.codex/state_5.sqlite (file)",
"state DB integrity": "ok",
"thread history DB": "/Users/brianwhitton/.codex/thread_history_1.sqlite (missing)",
"thread history DB integrity": "skipped (missing)"
},
"remediation": null,
"durationMs": 724
},
"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": "370",
"rollout DB active rows": "370",
"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=370",
"rollout DB rows": "370",
"rollout DB scan cap reached": "false",
"rollout DB scan errors": "0",
"rollout DB sources": "cli=306, subagent:thread_spawn=64",
"rollout DB stale rows": "0"
},
"remediation": null,
"durationMs": 59
},
"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": "Mac OS 26.5.2 [64-bit]",
"os language": "en-US",
"os type": "Mac OS",
"os version": "26.5.2"
},
"remediation": null,
"durationMs": 2
},
"terminal.env": {
"id": "terminal.env",
"category": "terminal",
"status": "ok",
"summary": "terminal metadata was detected",
"details": {
"COLORFGBG": "15;0",
"COLORTERM": "truecolor",
"TERMINFO_DIRS entry": [
"/Applications/iTerm.app/Contents/Resources/terminfo (dir)",
"/usr/share/terminfo (dir)"
],
"TERM_PROGRAM": "iTerm.app",
"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": "iTerm2",
"terminal size": "196x49",
"terminal version": "3.6.11"
},
"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": "tank3",
"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": "0.146.0",
"check for update on startup": "true",
"dismissed version": "0.122.0",
"last checked at": "2026-08-04T13:53:31.390151Z",
"latest version": "0.147.0",
"latest version status": "newer version is available",
"update action": "brew upgrade --cask codex",
"version cache": "/Users/brianwhitton/.codex/version.json"
},
"remediation": null,
"durationMs": 91
}
}
}What issue are you seeing?
codex spontaneously generates long lists of names and "You have #### tokens left", over and over again and it eats up all my tokens.
What steps can reproduce the bug?
Uploaded thread: 019fe495-38e3-7213-8f61-d312a36c65d8
What is the expected behavior?
not doing that
Additional information
_No response_
1 Comment
Identifying the repeated message from the source: "You have #### tokens left" is codex's token-budget reminder (template: "Your context window is nearly exhausted (only {n_remaining} tokens remaining) and will be automatically reset for you soon…",
core/src/config/mod.rs#L1072). It's injected as model-visible input at configured remaining-token thresholds, deduped per context window (https://github.com/openai/codex/blob/1f41cc5d92/codex-rs/core/src/rollout_budget.rs#L67-L110) — so after every compaction/window reset the delivery state re-arms and the reminder legitimately fires again (rearm_reminder, re-armed from session handlers). A session hovering near its limit therefore compacts → gets reminded → fills up → compacts → gets reminded, indefinitely; each reminder is itself input the model responds to, which compounds usage. If the "long lists of names" appear next to these reminders, that's consistent with the model reacting badly to the repeated "notes and history items will be persistent" instruction — degenerate looping on an injected system notice.Repo-side improvements that would bound this: a per-session cap on total reminder deliveries (not just per-window), and skipping re-delivery when the previous window already hit the max threshold — the current keying guarantees recurrence in exactly the long-running sessions where the reminder costs most. If you can share the thread ID's
/statusor a screenshot showing the surrounding output, it would confirm whether the name lists come from the model's response to these reminders or from something else.