config-sample.md Codex Docs, 2026-02-19 20:37 UTC → 2026-03-05 18:41 UTC

1# Sample Configuration1# Sample Configuration

2 2 

3A complete example config.toml you can copy and adapt3Use this example configuration as a starting point. It includes most keys Codex reads from `config.toml`, along with default behaviors, recommended values where helpful, and short notes.

4 

5Use this example configuration as a starting point. It includes most keys Codex reads from `config.toml`, along with defaults and short notes.

6 4 

7For explanations and guidance, see:5For explanations and guidance, see:

8 6 

9- [Config basics](https://developers.openai.com/codex/config-basic)7- [Config basics](https://developers.openai.com/codex/config-basic)

10- [Advanced Config](https://developers.openai.com/codex/config-advanced)8- [Advanced Config](https://developers.openai.com/codex/config-advanced)

11- [Config Reference](https://developers.openai.com/codex/config-reference)9- [Config Reference](https://developers.openai.com/codex/config-reference)

10- [Sandbox and approvals](https://developers.openai.com/codex/security#sandbox-and-approvals)

11- [Managed configuration](https://developers.openai.com/codex/security#managed-configuration)

12 12 

13Use the snippet below as a reference. Copy only the keys and sections you need into `~/.codex/config.toml` (or into a project-scoped `.codex/config.toml`), then adjust values for your setup.13Use the snippet below as a reference. Copy only the keys and sections you need into `~/.codex/config.toml` (or into a project-scoped `.codex/config.toml`), then adjust values for your setup.

14 14 

15```toml15```toml

16# Codex example configuration (config.toml)16# Codex example configuration (config.toml)

17#17#

18# This file lists all keys Codex reads from config.toml, their default values,18# This file lists all keys Codex reads from config.toml, along with default

19# and concise explanations. Values here mirror the effective defaults compiled19# behaviors, recommended examples, and concise explanations. Adjust as needed.

20# into the CLI. Adjust as needed.

21#20#

22# Notes21# Notes

23# - Root keys must appear before tables in TOML.22# - Root keys must appear before tables in TOML.

28# Core Model Selection27# Core Model Selection

29################################################################################28################################################################################

30 29 

31# Primary model used by Codex. Default: "gpt-5.2-codex" on all platforms.30# Primary model used by Codex. Recommended example for most users: "gpt-5.4".

32model = "gpt-5.2-codex"31model = "gpt-5.4"

33 32 

34# Default communication style for supported models. Default: "friendly".33# Default communication style for supported models. Default: "friendly".

35# Allowed values: none | friendly | pragmatic34# Allowed values: none | friendly | pragmatic

36# personality = "friendly"35# personality = "friendly"

37 36 

38# Optional model override for /review. Default: unset (uses current session model).37# Optional model override for /review. Default: unset (uses current session model).

39# review_model = "gpt-5.2-codex"38# review_model = "gpt-5.4"

40 39 

41# Provider id selected from [model_providers]. Default: "openai".40# Provider id selected from [model_providers]. Default: "openai".

42model_provider = "openai"41model_provider = "openai"

48# Uncomment to force values.47# Uncomment to force values.

49# model_context_window = 128000 # tokens; default: auto for model48# model_context_window = 128000 # tokens; default: auto for model

50# model_auto_compact_token_limit = 0 # tokens; unset uses model defaults49# model_auto_compact_token_limit = 0 # tokens; unset uses model defaults

51# tool_output_token_limit = 10000 # tokens stored per tool output; default: 10000 for gpt-5.2-codex50# tool_output_token_limit = 10000 # tokens stored per tool output

51# model_catalog_json = "/absolute/path/to/models.json" # optional startup-only model catalog override

52# background_terminal_max_timeout = 300000 # ms; max empty write_stdin poll window (default 5m)

52# log_dir = "/absolute/path/to/codex-logs" # directory for Codex logs; default: "$CODEX_HOME/log"53# log_dir = "/absolute/path/to/codex-logs" # directory for Codex logs; default: "$CODEX_HOME/log"

54# sqlite_home = "/absolute/path/to/codex-state" # optional SQLite-backed runtime state directory

53 55 

54################################################################################56################################################################################

55# Reasoning & Verbosity (Responses API capable models)57# Reasoning & Verbosity (Responses API capable models)

56################################################################################58################################################################################

57 59 

58# Reasoning effort: minimal | low | medium | high | xhigh (default: medium; xhigh on gpt-5.2-codex and gpt-5.2)60# Reasoning effort: minimal | low | medium | high | xhigh (default: medium; `xhigh` availability is model-dependent)

59model_reasoning_effort = "medium"61model_reasoning_effort = "medium"

60 62 

61# Reasoning summary: auto | concise | detailed | none (default: auto)63# Reasoning summary: auto | concise | detailed | none (default: auto)

107# - untrusted: only known-safe read-only commands auto-run; others prompt109# - untrusted: only known-safe read-only commands auto-run; others prompt

108# - on-request: model decides when to ask (default)110# - on-request: model decides when to ask (default)

109# - never: never prompt (risky)111# - never: never prompt (risky)

112# - { reject = { ... } }: auto-reject selected prompt categories

110approval_policy = "on-request"113approval_policy = "on-request"

114# Example granular auto-reject policy:

115# approval_policy = { reject = { sandbox_approval = true, rules = false, mcp_elicitations = false } }

116 

117# Allow login-shell semantics for shell-based tools when they request `login = true`.

118# Default: true. Set false to force non-login shells and reject explicit login-shell requests.

119allow_login_shell = true

111 120 

112# Filesystem/network sandbox policy for tool calls:121# Filesystem/network sandbox policy for tool calls:

113# - read-only (default)122# - read-only (default)

115# - danger-full-access (no sandbox; extremely risky)124# - danger-full-access (no sandbox; extremely risky)

116sandbox_mode = "read-only"125sandbox_mode = "read-only"

117 126 

127[windows]

128# Native Windows sandbox mode (Windows only): unelevated | elevated

129sandbox = "unelevated"

130 

118################################################################################131################################################################################

119# Authentication & Login132# Authentication & Login

120################################################################################133################################################################################

138# Optional fixed port for MCP OAuth callback: 1-65535. Default: unset.151# Optional fixed port for MCP OAuth callback: 1-65535. Default: unset.

139# mcp_oauth_callback_port = 4321152# mcp_oauth_callback_port = 4321

140 153 

154# Optional redirect URI override for MCP OAuth login (for example, remote devbox ingress).

155# Custom callback paths are supported. `mcp_oauth_callback_port` still controls the listener port.

156# mcp_oauth_callback_url = "https://devbox.example.internal/callback"

157 

141################################################################################158################################################################################

142# Project Documentation Controls159# Project Documentation Controls

143################################################################################160################################################################################

194# Active profile name. When unset, no profile is applied.211# Active profile name. When unset, no profile is applied.

195# profile = "default"212# profile = "default"

196 213 

214################################################################################

215# Agents (multi-agent roles and limits)

216################################################################################

217 

218# [agents]

219# Maximum concurrently open agent threads. Default: 6

220# max_threads = 6

221# Maximum nested spawn depth. Root session starts at depth 0. Default: 1

222# max_depth = 1

223# Default timeout per worker for spawn_agents_on_csv jobs. When unset, the tool defaults to 1800 seconds.

224# job_max_runtime_seconds = 1800

225 

226# [agents.reviewer]

227# description = "Find security, correctness, and test risks in code."

228# config_file = "./agents/reviewer.toml" # relative to the config.toml that defines it

229 

197################################################################################230################################################################################

198# Skills (per-skill overrides)231# Skills (per-skill overrides)

199################################################################################232################################################################################

200 233 

201# Disable or re-enable a specific skill without deleting it.234# Disable or re-enable a specific skill without deleting it.

202[[skills.config]]235[[skills.config]]

203# path = "/path/to/skill"236# path = "/path/to/skill/SKILL.md"

204# enabled = false237# enabled = false

205 238 

206################################################################################239################################################################################

276# Control alternate screen usage (auto skips it in Zellij to preserve scrollback).309# Control alternate screen usage (auto skips it in Zellij to preserve scrollback).

277# alternate_screen = "auto"310# alternate_screen = "auto"

278 311 

279# Ordered list of footer status-line item IDs. Default: null (disabled).312# Ordered list of footer status-line item IDs. When unset, Codex uses:

313# ["model-with-reasoning", "context-remaining", "current-dir"].

314# Set to [] to hide the footer.

280# status_line = ["model", "context-remaining", "git-branch"]315# status_line = ["model", "context-remaining", "git-branch"]

281 316 

317# Syntax-highlighting theme (kebab-case). Use /theme in the TUI to preview and save.

318# You can also add custom .tmTheme files under $CODEX_HOME/themes.

319# theme = "catppuccin-mocha"

320 

282# Control whether users can submit feedback from `/feedback`. Default: true321# Control whether users can submit feedback from `/feedback`. Default: true

283[feedback]322[feedback]

284enabled = true323enabled = true

301 340 

302[features]341[features]

303# Leave this table empty to accept defaults. Set explicit booleans to opt in/out.342# Leave this table empty to accept defaults. Set explicit booleans to opt in/out.

304shell_tool = true343# shell_tool = true

305# apps = false344# apps = false

306# apps_mcp_gateway = false345# apps_mcp_gateway = false

307# Deprecated legacy toggles; prefer the top-level `web_search` setting.

308# web_search = false

309# web_search_cached = false346# web_search_cached = false

310# web_search_request = false347# web_search_request = false

311unified_exec = false348# unified_exec = false

312shell_snapshot = false349# shell_snapshot = false

313apply_patch_freeform = false350# apply_patch_freeform = false

351# multi_agent = false

314# search_tool = false352# search_tool = false

315# personality = true353# personality = true

316request_rule = true354# request_rule = true

317collaboration_modes = true355# collaboration_modes = true

318use_linux_sandbox_bwrap = false356# use_linux_sandbox_bwrap = false

319experimental_windows_sandbox = false357# remote_models = false

320elevated_windows_sandbox = false358# runtime_metrics = false

321remote_models = false359# powershell_utf8 = true

322runtime_metrics = false360# child_agents_md = false

323powershell_utf8 = true

324child_agents_md = false

325 361 

326################################################################################362################################################################################

327# Define MCP servers under this table. Leave empty to disable.363# Define MCP servers under this table. Leave empty to disable.

401[profiles]437[profiles]

402 438 

403# [profiles.default]439# [profiles.default]

404# model = "gpt-5.2-codex"440# model = "gpt-5.4"

405# model_provider = "openai"441# model_provider = "openai"

406# approval_policy = "on-request"442# approval_policy = "on-request"

407# sandbox_mode = "read-only"443# sandbox_mode = "read-only"

411# model_verbosity = "medium"447# model_verbosity = "medium"

412# personality = "friendly" # or "pragmatic" or "none"448# personality = "friendly" # or "pragmatic" or "none"

413# chatgpt_base_url = "https://chatgpt.com/backend-api/"449# chatgpt_base_url = "https://chatgpt.com/backend-api/"

450# model_catalog_json = "./models.json"

414# experimental_compact_prompt_file = "./compact_prompt.txt"451# experimental_compact_prompt_file = "./compact_prompt.txt"

415# include_apply_patch_tool = false452# include_apply_patch_tool = false

416# experimental_use_unified_exec_tool = false453# experimental_use_unified_exec_tool = false

424 461 

425# Optional per-app controls.462# Optional per-app controls.

426[apps]463[apps]

464# [_default] applies to all apps unless overridden per app.

465# [apps._default]

466# enabled = true

467# destructive_enabled = true

468# open_world_enabled = true

469#

427# [apps.google_drive]470# [apps.google_drive]

428# enabled = false471# enabled = false

429# disabled_reason = "user" # or "unknown"472# destructive_enabled = false # block destructive-hint tools for this app

473# default_tools_enabled = true

474# default_tools_approval_mode = "prompt" # auto | prompt | approve

475#

476# [apps.google_drive.tools."files/delete"]

477# enabled = false

478# approval_mode = "approve"

430 479 

431################################################################################480################################################################################

432# Projects (trust levels)481# Projects (trust levels)

477# client-certificate = "/etc/codex/certs/client.pem"526# client-certificate = "/etc/codex/certs/client.pem"

478# client-private-key = "/etc/codex/certs/client-key.pem"527# client-private-key = "/etc/codex/certs/client-key.pem"

479```528```

529 

530################################################################################

531 

532# Windows

533 

534################################################################################

535 

536[windows]

537 

538# Native Windows sandbox mode (Windows only). The example below uses the

539 

540# recommended elevated mode.

541 

542sandbox = “elevated”