config-advanced diff

config-advanced.md +219 −36

Details

2 2

3Use these options when you need more control over providers, policies, and integrations. For a quick start, see [Config basics](https://developers.openai.com/codex/config-basic).3Use these options when you need more control over providers, policies, and integrations. For a quick start, see [Config basics](https://developers.openai.com/codex/config-basic).

4 4

5For background on project guidance, reusable capabilities, custom slash commands, subagent workflows, and integrations, see [Customization](https://developers.openai.com/codex/concepts/customization). For configuration keys, see [Configuration Reference](https://developers.openai.com/codex/config-reference).

5## Profiles7## Profiles

6 8

7Profiles let you save named sets of configuration values and switch between them from the CLI.9Profiles let you save named sets of configuration values and switch between them from the CLI.

13Define profiles under `[profiles.<name>]` in `config.toml`, then run `codex --profile <name>`:15Define profiles under `[profiles.<name>]` in `config.toml`, then run `codex --profile <name>`:

14 16

15```toml17```toml

~~16model = "gpt-5-codex"~~18model = "gpt-5.4"

17approval_policy = "on-request"19approval_policy = "on-request"

20model_catalog_json = "/Users/me/.codex/model-catalogs/default.json"

18 21

19[profiles.deep-review]22[profiles.deep-review]

20model = "gpt-5-pro"23model = "gpt-5-pro"

21model_reasoning_effort = "high"24model_reasoning_effort = "high"

22approval_policy = "never"25approval_policy = "never"

26model_catalog_json = "/Users/me/.codex/model-catalogs/deep-review.json"

23 27

24[profiles.lightweight]28[profiles.lightweight]

25model = "gpt-4.1"29model = "gpt-4.1"

28 32

29To make a profile the default, add `profile = "deep-review"` at the top level of `config.toml`. Codex loads that profile unless you override it on the command line.33To make a profile the default, add `profile = "deep-review"` at the top level of `config.toml`. Codex loads that profile unless you override it on the command line.

30 34

35Profiles can also override `model_catalog_json`. When both the top level and the selected profile set `model_catalog_json`, Codex prefers the profile value.

31## One-off overrides from the CLI37## One-off overrides from the CLI

32 38

33In addition to editing `~/.codex/config.toml`, you can override configuration for a single run from the CLI:39In addition to editing `~/.codex/config.toml`, you can override configuration for a single run from the CLI:

39 45

40```shell46```shell

41# Dedicated flag47# Dedicated flag

~~42codex --model gpt-5.2~~48codex --model gpt-5.4

43 49

44# Generic key/value override (value is TOML, not JSON)50# Generic key/value override (value is TOML, not JSON)

~~45codex --config model='"gpt-5.2"'~~51codex --config model='"gpt-5.4"'

46codex --config sandbox_workspace_write.network_access=true52codex --config sandbox_workspace_write.network_access=true

47codex --config 'shell_environment_policy.include_only=["PATH","HOME"]'53codex --config 'shell_environment_policy.include_only=["PATH","HOME"]'

48```54```

68 74

69For shared defaults, rules, and skills checked into repos or system paths, see [Team Config](https://developers.openai.com/codex/enterprise/admin-setup#team-config).75For shared defaults, rules, and skills checked into repos or system paths, see [Team Config](https://developers.openai.com/codex/enterprise/admin-setup#team-config).

70 76

71If you just need to point the built-in OpenAI provider at an LLM proxy, router, or data-residency enabled project, set environment variable `OPENAI_BASE_URL` instead of defining a new provider. This overrides the default OpenAI endpoint without a `config.toml` change.77If you just need to point the built-in OpenAI provider at an LLM proxy, router, or data-residency enabled project, set `openai_base_url` in `config.toml` instead of defining a new provider. This changes the base URL for the built-in `openai` provider without requiring a separate `model_providers.<id>` entry.

72 78

73```toml79```toml

~~74export OPENAI_BASE_URL="https://api.openai.com/v1"~~80openai_base_url = "https://us.api.openai.com/v1"

~~75codex~~

76```81```

77 82

78## Project config files (`.codex/config.toml`)83## Project config files (`.codex/config.toml`)

79 84

80In addition to your user config, Codex reads project-scoped overrides from `.codex/config.toml` files inside your repo. Codex walks from the project root to your current working directory and loads every `.codex/config.toml` it finds. If multiple files define the same key, the closest file to your working directory wins.85In addition to your user config, Codex reads project-scoped overrides from `.codex/config.toml` files inside your repo. Codex walks from the project root to your current working directory and loads every `.codex/config.toml` it finds. If multiple files define the same key, the closest file to your working directory wins.

81 86

~~82For security, Codex loads project-scoped config files only when the project is trusted. If the project is untrusted, Codex ignores `.codex/config.toml` files in the project.~~87For security, Codex loads project-scoped config files only when the project is trusted. If the project is untrusted, Codex ignores project `.codex/` layers, including `.codex/config.toml`, project-local hooks, and project-local rules. User and system layers remain separate and still load.

89Relative paths inside a project config (for example, `model_instructions_file`) are resolved relative to the `.codex/` folder that contains the `config.toml`.

91## Hooks (experimental)

93Codex can also load lifecycle hooks from `hooks.json` files that sit next to

94active config layers.

83 95

~~84Relative paths inside a project config (for example, `experimental_instructions_file`) are resolved relative to the `.codex/` folder that contains the `config.toml`.~~96In practice, the two most useful locations are:

98- `~/.codex/hooks.json`

99- `<repo>/.codex/hooks.json`

100

101Project-local hooks load only when the project `.codex/` layer is trusted.

102User-level hooks remain independent of project trust.

103

104Turn hooks on with:

105

106```toml

107[features]

108codex_hooks = true

109```

110

111For the current event list, input fields, output behavior, and limitations, see

112[Hooks](https://developers.openai.com/codex/hooks).

85 113

86## Agent roles (`[agents]` in `config.toml`)114## Agent roles (`[agents]` in `config.toml`)

87 115

~~88For multi-agent role configuration (`[agents]` in `config.toml`), see [Multi-agents](https://developers.openai.com/codex/multi-agent).~~116For subagent role configuration (`[agents]` in `config.toml`), see [Subagents](https://developers.openai.com/codex/subagents).

89 117

90## Project root detection118## Project root detection

91 119

102 130

103## Custom model providers131## Custom model providers

104 132

105A model provider defines how Codex connects to a model (base URL, wire API, and optional HTTP headers).133A model provider defines how Codex connects to a model (base URL, wire API, authentication, and optional HTTP headers). Custom providers can't reuse the reserved built-in provider IDs: `openai`, `ollama`, and `lmstudio`.

106 134

107Define additional providers and point `model_provider` at them:135Define additional providers and point `model_provider` at them:

108 136

109```toml137```toml

110model = "gpt-5.1"138model = "gpt-5.4"

111model_provider = "proxy"139model_provider = "proxy"

112 140

113[model_providers.proxy]141[model_providers.proxy]

115base_url = "http://proxy.example.com"143base_url = "http://proxy.example.com"

116env_key = "OPENAI_API_KEY"144env_key = "OPENAI_API_KEY"

117 145

118[model_providers.ollama]146[model_providers.local_ollama]

119name = "Ollama"147name = "Ollama"

120base_url = "http://localhost:11434/v1"148base_url = "http://localhost:11434/v1"

121 149

133env_http_headers = { "X-Example-Features" = "EXAMPLE_FEATURES" }161env_http_headers = { "X-Example-Features" = "EXAMPLE_FEATURES" }

134```162```

135 163

164Use command-backed authentication when a provider needs Codex to fetch bearer tokens from an external credential helper:

165

166```toml

167[model_providers.proxy]

168name = "OpenAI using LLM proxy"

169base_url = "https://proxy.example.com/v1"

170wire_api = "responses"

171

172[model_providers.proxy.auth]

173command = "/usr/local/bin/fetch-codex-token"

174args = ["--audience", "codex"]

175timeout_ms = 5000

176refresh_interval_ms = 300000

177```

178

179The auth command receives no `stdin` and must print the token to stdout. Codex trims surrounding whitespace, treats an empty token as an error, and refreshes proactively at `refresh_interval_ms`; set `refresh_interval_ms = 0` to refresh only after an authentication retry. Don't combine `[model_providers.<id>.auth]` with `env_key`, `experimental_bearer_token`, or `requires_openai_auth`.

180

136## OSS mode (local providers)181## OSS mode (local providers)

137 182

138Codex can run against a local "open source" provider (for example, Ollama or LM Studio) when you pass `--oss`. If you pass `--oss` without specifying a provider, Codex uses `oss_provider` as the default.183Codex can run against a local "open source" provider (for example, Ollama or LM Studio) when you pass `--oss`. If you pass `--oss` without specifying a provider, Codex uses `oss_provider` as the default.

151env_key = "AZURE_OPENAI_API_KEY"196env_key = "AZURE_OPENAI_API_KEY"

152query_params = { api-version = "2025-04-01-preview" }197query_params = { api-version = "2025-04-01-preview" }

153wire_api = "responses"198wire_api = "responses"

~~154~~

155[model_providers.openai]

156request_max_retries = 4199request_max_retries = 4

157stream_max_retries = 10200stream_max_retries = 10

158stream_idle_timeout_ms = 300000201stream_idle_timeout_ms = 300000

159```202```

160 203

204To change the base URL for the built-in OpenAI provider, use `openai_base_url`; don't create `[model_providers.openai]`, because you can't override built-in provider IDs.

205

161## ChatGPT customers using data residency206## ChatGPT customers using data residency

162 207

163Projects created with [data residency](https://help.openai.com/en/articles/9903489-data-residency-and-inference-residency-for-chatgpt) enabled can create a model provider to update the base_url with the [correct prefix](https://platform.openai.com/docs/guides/your-data#which-models-and-features-are-eligible-for-data-residency).208Projects created with [data residency](https://help.openai.com/en/articles/9903489-data-residency-and-inference-residency-for-chatgpt) enabled can create a model provider to update the base_url with the [correct prefix](https://platform.openai.com/docs/guides/your-data#which-models-and-features-are-eligible-for-data-residency).

182 227

183## Approval policies and sandbox modes228## Approval policies and sandbox modes

184 229

185Pick approval strictness (affects when Codex pauses) and sandbox level (affects file/network access). See [Sandbox & approvals](https://developers.openai.com/codex/security) for deeper examples.230Pick approval strictness (affects when Codex pauses) and sandbox level (affects file/network access).

186 231

187```232For operational details to keep in mind while editing `config.toml`, see [Common sandbox and approval combinations](https://developers.openai.com/codex/agent-approvals-security#common-sandbox-and-approval-combinations), [Protected paths in writable roots](https://developers.openai.com/codex/agent-approvals-security#protected-paths-in-writable-roots), and [Network access](https://developers.openai.com/codex/agent-approvals-security#network-access).

188approval_policy = "untrusted" # Other options: on-request, never233

234You can also use a granular approval policy (`approval_policy = { granular = { ... } }`) to allow or auto-reject individual prompt categories. This is useful when you want normal interactive approvals for some cases but want others, such as `request_permissions` or skill-script prompts, to fail closed automatically.

235

236Set `approvals_reviewer = "auto_review"` to route eligible interactive approval

237requests through automatic review. This changes the reviewer, not the sandbox

238boundary.

239

240Use `[auto_review].policy` for local reviewer policy instructions. Managed

241`guardian_policy_config` takes precedence.

242

243```toml

244approval_policy = "untrusted" # Other options: on-request, never, or { granular = { ... } }

245approvals_reviewer = "user" # Or "auto_review" for automatic review

189sandbox_mode = "workspace-write"246sandbox_mode = "workspace-write"

247allow_login_shell = false # Optional hardening: disallow login shells for shell tools

248

249# Example granular approval policy:

250# approval_policy = { granular = {

251# sandbox_approval = true,

252# rules = true,

253# mcp_elicitations = true,

254# request_permissions = false,

255# skill_approval = false

256# } }

190 257

191[sandbox_workspace_write]258[sandbox_workspace_write]

192exclude_tmpdir_env_var = false # Allow $TMPDIR259exclude_tmpdir_env_var = false # Allow $TMPDIR

193exclude_slash_tmp = false # Allow /tmp260exclude_slash_tmp = false # Allow /tmp

194writable_roots = ["/Users/YOU/.pyenv/shims"]261writable_roots = ["/Users/YOU/.pyenv/shims"]

195network_access = false # Opt in to outbound network262network_access = false # Opt in to outbound network

263

264[auto_review]

265policy = """

266Use your organization's automatic review policy.

267"""

196```268```

197 269

270Need the complete key list (including profile-scoped overrides and requirements constraints)? See [Configuration Reference](https://developers.openai.com/codex/config-reference) and [Managed configuration](https://developers.openai.com/codex/enterprise/managed-configuration).

271

198In workspace-write mode, some environments keep `.git/` and `.codex/`272In workspace-write mode, some environments keep `.git/` and `.codex/`

199 read-only even when the rest of the workspace is writable. This is why273 read-only even when the rest of the workspace is writable. This is why

200 commands like `git commit` may still require approval to run outside the274 commands like `git commit` may still require approval to run outside the

291 365

292For more security and privacy guidance around telemetry, see [Security](https://developers.openai.com/codex/security#monitoring-and-telemetry).366For more security and privacy guidance around telemetry, see [Security](https://developers.openai.com/codex/agent-approvals-security#monitoring-and-telemetry).

293 367

294### Metrics368### Metrics

295 369

312 386

313#### Metrics catalog387#### Metrics catalog

314 388

315Each metric includes the required fields plus the default context fields above. Every metric is prefixed by `codex.`.389Each metric includes the required fields plus the default context fields above. Metric names below omit the `codex.` prefix.

390Most metric names are centralized in `codex-rs/otel/src/metrics/names.rs`; feature-specific metrics emitted outside that file are included here too.

316If a metric includes the `tool` field, it reflects the internal tool used (for example, `apply_patch` or `shell`) and doesn't contain the actual shell command or patch `codex` is trying to apply.391If a metric includes the `tool` field, it reflects the internal tool used (for example, `apply_patch` or `shell`) and doesn't contain the actual shell command or patch `codex` is trying to apply.

317 392

393#### Runtime and model transport

394

396| --- | --- | --- | --- |

420

421The `cloud_requirements.fetch_attempt` metric includes `trigger`, `attempt`, `outcome`, and `status_code` fields. The `cloud_requirements.fetch_final` metric includes `trigger`, `outcome`, `reason`, `attempt_count`, and `status_code` fields.

422

423#### Turn and tool activity

424

426| --- | --- | --- | --- |

445

446The `mcp.call` and `mcp.call.duration_ms` metrics include `status`; normal tool-call emissions also include `tool`, plus `connector_id` and `connector_name` when available. Blocked Codex Apps MCP calls may emit `mcp.call` with only `status`.

447

448#### Threads, tasks, and features

449

319| --- | --- | --- | --- |451| --- | --- | --- | --- |

475

476The `shell_snapshot` metric includes `success` and, on failures, `failure_reason`.

477

478#### Memory and local state

479

481| --- | --- | --- | --- |

497The `external_agent_config.detect` and `external_agent_config.import` metrics include `migration_type`; skills migrations also include `skills_count`.

498

499#### Windows sandbox

500

502| --- | --- | --- | --- |

521

522The elevated setup failure metrics include `code` and `message` when Windows setup failure details are available, and may include `originator` when emitted from the shared setup path. The `windows_sandbox.legacy_setup_preflight_failed` metric includes `originator` when emitted from the shared setup path, but fallback-prompt preflight failures may not include any fields.

344 523

345### Feedback controls524### Feedback controls

346 525

418- `notify` runs an external program (good for webhooks, desktop notifiers, CI hooks).597- `notify` runs an external program (good for webhooks, desktop notifiers, CI hooks).

419- `tui.notifications` is built in to the TUI and can optionally filter by event type (for example, `agent-turn-complete` and `approval-requested`).598- `tui.notifications` is built in to the TUI and can optionally filter by event type (for example, `agent-turn-complete` and `approval-requested`).

420- `tui.notification_method` controls how the TUI emits terminal notifications (`auto`, `osc9`, or `bel`).599- `tui.notification_method` controls how the TUI emits terminal notifications (`auto`, `osc9`, or `bel`).

600- `tui.notification_condition` controls whether TUI notifications fire only when

601 the terminal is `unfocused` or `always`.

421 602

422In `auto` mode, Codex prefers OSC 9 notifications (a terminal escape sequence some terminals interpret as a desktop notification) and falls back to BEL (`\x07`) otherwise.603In `auto` mode, Codex prefers OSC 9 notifications (a terminal escape sequence some terminals interpret as a desktop notification) and falls back to BEL (`\x07`) otherwise.

423 604

464 645

465- `tui.notifications`: enable/disable notifications (or restrict to specific types)646- `tui.notifications`: enable/disable notifications (or restrict to specific types)

466- `tui.notification_method`: choose `auto`, `osc9`, or `bel` for terminal notifications647- `tui.notification_method`: choose `auto`, `osc9`, or `bel` for terminal notifications

648- `tui.notification_condition`: choose `unfocused` or `always` for when

649 notifications fire

467- `tui.animations`: enable/disable ASCII animations and shimmer effects650- `tui.animations`: enable/disable ASCII animations and shimmer effects

468- `tui.alternate_screen`: control alternate screen usage (set to `never` to keep terminal scrollback)651- `tui.alternate_screen`: control alternate screen usage (set to `never` to keep terminal scrollback)

469- `tui.show_tooltips`: show or hide onboarding tooltips on the welcome screen652- `tui.show_tooltips`: show or hide onboarding tooltips on the welcome screen

config-advanced.md Codex Docs, 2026-02-19 20:53 UTC → 2026-04-24 18:20 UTC