Codex ignores model_reasoning_effort on new session startup
Open 💬 4 comments Opened Jun 13, 2026 by agustinrromero
What version of Codex CLI is running?
codex-cli 0.139.0
What subscription do you have?
Enterprise
Which model were you using?
_No response_
What platform is your computer?
Linux 7.0.12-100.fc43.x86_64 x86_64 unknown
What terminal emulator and version are you using (if applicable)?
Alacritty + Tmux
Codex doctor report
{
"schemaVersion": 1,
"generatedAt": "1781379382s since unix epoch",
"overallStatus": "warning",
"codexVersion": "0.139.0",
"checks": {
"app_server.status": {
"id": "app_server.status",
"category": "app-server",
"status": "ok",
"summary": "background server is not running",
"details": {
"control socket": "/home/agustinrromero/.codex/app-server-control/app-server-control.sock",
"daemon state dir": "/home/agustinrromero/.codex/app-server-daemon",
"mode": "ephemeral",
"pid file": "/home/agustinrromero/.codex/app-server-daemon/app-server.pid (missing)",
"settings": "/home/agustinrromero/.codex/app-server-daemon/settings.json (missing)",
"status": "not running",
"update-loop pid file": "/home/agustinrromero/.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": "/home/agustinrromero/.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/agustinrromero/.codex",
"config.toml": "/home/agustinrromero/.codex/config.toml",
"config.toml parse": "ok",
"cwd": "/home/agustinrromero/.codex",
"enabled feature flags": "shell_tool, unified_exec, shell_snapshot, terminal_resize_reflow, sqlite, apply_patch_streaming_events, hooks, enable_request_compression, multi_agent, multi_agent_v2, apps, tool_suggest, plugins, in_app_browser, browser_use, browser_use_external, computer_use, plugin_sharing, image_generation, skill_mcp_dependency_install, steer, guardian_approval, goals, collaboration_modes, tool_call_mcp_elicitation, personality, fast_mode, tui_app_server, prevent_idle_sleep, workspace_dependencies",
"feature flag overrides": "apply_patch_streaming_events=true, multi_agent_v2=true, prevent_idle_sleep=true",
"feature flags enabled": "30",
"log dir": "/home/agustinrromero/.codex/log",
"mcp servers": "2",
"model": "gpt-5.5",
"model provider": "openai",
"sqlite home": "/home/agustinrromero/.codex"
},
"remediation": null,
"durationMs": 0
},
"git.environment": {
"id": "git.environment",
"category": "git",
"status": "ok",
"summary": "git version 2.54.0",
"details": {
"PATH git #1": "/usr/bin/git",
"PATH git entries": "1",
"git build options": "git version 2.54.0; cpu: x86_64; no commit associated with this build; sizeof-long: 8; sizeof-size_t: 8; shell-path: /bin/sh; rust: disabled; gettext: enabled; libcurl: 8.15.0; OpenSSL: OpenSSL 3.5.4 30 Sep 2025; zlib-ng: 2.3.3; SHA-1: SHA1_DC; SHA-256: SHA256_BLK; default-ref-format: files; default-hash: sha1",
"git exec path": "/usr/libexec/git-core",
"git version": "git version 2.54.0",
"repo detected": "false",
"selected git": "/usr/bin/git"
},
"remediation": null,
"durationMs": 51
},
"installation": {
"id": "installation",
"category": "install",
"status": "ok",
"summary": "installation looks consistent",
"details": {
"PATH codex #1": "/home/agustinrromero/.config/nvm/versions/node/v22.21.1/bin/codex",
"current executable": "/home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
"install context": "npm (package /home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
"managed by bun": "false",
"managed by npm": "true",
"managed package root": "/home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex",
"npm update target": "/home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex"
},
"remediation": null,
"durationMs": 146
},
"mcp.config": {
"id": "mcp.config",
"category": "mcp",
"status": "warning",
"summary": "MCP configuration has optional issues",
"details": {
"configured servers": "2",
"disabled servers": "0",
"playwright": "env var REMOTE_ENV is not set",
"stdio servers": "2"
},
"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": 590
},
"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",
"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": 682
},
"runtime.provenance": {
"id": "runtime.provenance",
"category": "runtime",
"status": "ok",
"summary": "running npm on linux-x86_64",
"details": {
"commit": "unknown",
"current executable": "/home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
"install method": "npm (package /home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
"platform": "linux-x86_64",
"version": "0.139.0"
},
"remediation": null,
"durationMs": 0
},
"runtime.search": {
"id": "runtime.search",
"category": "search",
"status": "ok",
"summary": "search is OK (bundled)",
"details": {
"search command": "/home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/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": "/home/agustinrromero/.codex/tmp/arg0/codex-arg0ebJBfs/codex-linux-sandbox",
"execve wrapper helper": "/home/agustinrromero/.codex/tmp/arg0/codex-arg0ebJBfs/codex-execve-wrapper",
"filesystem sandbox": "restricted",
"network sandbox": "enabled"
},
"remediation": null,
"durationMs": 0
},
"state.paths": {
"id": "state.paths",
"category": "state",
"status": "ok",
"summary": "state paths and databases are inspectable",
"details": {
"CODEX_HOME": "/home/agustinrromero/.codex (dir)",
"active rollout files": "778 files, 344401143 total bytes, 442674 average bytes",
"archived rollout files": "0 files, 0 total bytes, 0 average bytes",
"goals DB": "/home/agustinrromero/.codex/goals_1.sqlite (file)",
"goals DB integrity": "ok",
"log DB": "/home/agustinrromero/.codex/logs_2.sqlite (file)",
"log DB integrity": "ok",
"log dir": "/home/agustinrromero/.codex/log (missing)",
"memories DB": "/home/agustinrromero/.codex/memories_1.sqlite (file)",
"memories DB integrity": "ok",
"sqlite home": "/home/agustinrromero/.codex (dir)",
"state DB": "/home/agustinrromero/.codex/state_5.sqlite (file)",
"state DB integrity": "ok"
},
"remediation": null,
"durationMs": 1224
},
"state.rollout_db_parity": {
"id": "state.rollout_db_parity",
"category": "threads",
"status": "warning",
"summary": "rollout files and state DB thread inventory differ",
"details": {
"default model provider": "openai",
"rollout DB active files": "778",
"rollout DB active rows": "778",
"rollout DB archive mismatches": "0",
"rollout DB archived files": "0",
"rollout DB archived rows": "31",
"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=809",
"rollout DB rows": "809",
"rollout DB scan cap reached": "false",
"rollout DB scan errors": "0",
"rollout DB sources": "cli=467, unknown=275, subagent:thread_spawn=46, subagent:review=10, vscode=9, exec=2",
"rollout DB stale row sample": [
"/home/agustinrromero/.codex/archived_sessions/rollout-2026-03-12T23-57-14-019ce520-7051-78f2-b1d0-673b6835d6c5.jsonl",
"/home/agustinrromero/.codex/archived_sessions/rollout-2026-03-12T23-59-29-019ce522-7e67-77e2-9e7e-0bcd74b5eca7.jsonl",
"/home/agustinrromero/.codex/archived_sessions/rollout-2026-03-13T00-00-56-019ce523-d275-78b1-9973-0fd05a064fea.jsonl",
"/home/agustinrromero/.codex/archived_sessions/rollout-2026-03-13T00-02-28-019ce525-3a77-7b23-adab-65c8661ee3b8.jsonl",
"/home/agustinrromero/.codex/archived_sessions/rollout-2026-03-13T00-10-22-019ce52c-783f-7a03-8b7f-2649ff6fb8a3.jsonl"
],
"rollout DB stale rows": "31"
},
"issues": [
{
"severity": "warning",
"cause": "state DB rows point at missing or unusable rollout files",
"measured": "31 stale rows",
"expected": "every state DB rollout path is a file on disk",
"remedy": null,
"fields": []
}
],
"remediation": null,
"durationMs": 6702
},
"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": "Fedora 43.0.0 [64-bit]",
"os language": "en-US",
"os type": "Fedora",
"os version": "43.0.0"
},
"remediation": null,
"durationMs": 16
},
"terminal.env": {
"id": "terminal.env",
"category": "terminal",
"status": "ok",
"summary": "terminal metadata was detected",
"details": {
"COLORTERM": "truecolor",
"DISPLAY": "present",
"TERM": "xterm-256color",
"WAYLAND_DISPLAY": "present",
"color output": "disabled (stdout is not a terminal)",
"effective locale": "en_US.UTF-8",
"multiplexer": "tmux 3.5a",
"stderr is terminal": "true",
"stdin is terminal": "true",
"stdout is terminal": "false",
"terminal": "unknown",
"terminal size": "120x30",
"tmux allow-passthrough": "off",
"tmux client termname": "xterm-256color",
"tmux extended-keys": "off",
"tmux focus-events": "on",
"tmux set-clipboard": "external",
"tmux xterm-keys": "on"
},
"remediation": null,
"durationMs": 42
},
"terminal.title": {
"id": "terminal.title",
"category": "title",
"status": "ok",
"summary": "terminal title configured",
"details": {
"terminal title activity": "true",
"terminal title items": "activity, project-name, run-state, task-progress",
"terminal title project source": "cwd",
"terminal title project value": ".codex",
"terminal title source": "configured"
},
"remediation": null,
"durationMs": 0
},
"updates.status": {
"id": "updates.status",
"category": "updates",
"status": "ok",
"summary": "update configuration is locally consistent",
"details": {
"cached latest version": "0.139.0",
"check for update on startup": "true",
"dismissed version": "0.139.0",
"last checked at": "2026-06-13T18:41:48.223648857Z",
"latest version": "0.139.0",
"latest version status": "current version is not older",
"npm update target": "/home/agustinrromero/.config/nvm/versions/node/v22.21.1/lib/node_modules/@openai/codex",
"update action": "npm install -g @openai/codex",
"version cache": "/home/agustinrromero/.codex/version.json"
},
"remediation": null,
"durationMs": 427
}
}
}What issue are you seeing?
Codex CLI version: 0.139.0
Platform: Fedora 43, Linux x86_64
Auth mode: ChatGPT
Thread with investigation: 019ec25b-6c56-7802-a8eb-b82cf9a92450
My ~/.codex/config.toml contains:
model = "gpt-5.5"
model_reasoning_effort = "xhigh"
plan_mode_reasoning_effort = "xhigh"Expected behavior:
Starting any new Codex session should use gpt-5.5 with xhigh reasoning effort. The statusline item "model-with-reasoning" should show "gpt-5.5 xhigh".
Actual behavior:
New Codex sessions start as "gpt-5.5 low". This is not just a statusline display issue. The rollout files record effort=low for newly started sessions.
This happens both for new sessions and resumed sessions. Manual workaround is to open /model and set gpt-5.5 xhigh after startup.
Repro steps:
- Set ~/.codex/config.toml:
model = "gpt-5.5"
model_reasoning_effort = "xhigh"
plan_mode_reasoning_effort = "xhigh"
- Start a new Codex session.
- Observe statusline with "model-with-reasoning".
- Actual: shows "gpt-5.5 low".
- Expected: should show "gpt-5.5 xhigh".
Command-line repro:
codex debug app-server send-message-v2 'Reply with exactly OK.'
Observed thread/start response includes:
model: "gpt-5.5"
reasoningEffort: "low"
I also tried:
codex debug app-server -c model_reasoning_effort='"xhigh"' send-message-v2 'Reply with exactly OK.'
codex exec -c model_reasoning_effort='"xhigh"' --json 'Reply with exactly OK.'
Those still created turns whose rollout files recorded effort=low.
Relevant debug thread ids:
- 019ec273-6a4f-75a3-b745-2d360b8b1f8f: debug app-server fresh thread, returned reasoningEffort=low
- 019ec273-b2d3-7903-8488-6bd1aa472d7b: debug app-server with -c override, still returned reasoningEffort=low
- 019ec274-15ff-7b80-8d97-70c7c272823b: codex exec run, rollout recorded effort=low
Impact:
The documented config key model_reasoning_effort appears to be ignored by the startup/thread-start path, so every new session starts with low reasoning unless I manually change it.
What steps can reproduce the bug?
Uploaded thread: 019ec25b-6c56-7802-a8eb-b82cf
What is the expected behavior?
Starting any new Codex session should use gpt-5.5 with xhigh reasoning effort. The statusline item "model-with-reasoning" should show "gpt-5.5 xhigh".
Additional information
_No response_
This issue has 4 comments on GitHub. Read the full discussion on GitHub ↗