config-advanced diff

config-advanced.md +74 −18

Details

1# Advanced Configuration1# Advanced Configuration

2 2

~~3More advanced configuration options for Codex local clients~~

5Use 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).

6 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).

7## Profiles7## Profiles

8 8

9Profiles 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.

15Define 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>`:

16 16

17```toml17```toml

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

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

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

20 21

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

22model = "gpt-5-pro"23model = "gpt-5-pro"

23model_reasoning_effort = "high"24model_reasoning_effort = "high"

24approval_policy = "never"25approval_policy = "never"

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

25 27

26[profiles.lightweight]28[profiles.lightweight]

27model = "gpt-4.1"29model = "gpt-4.1"

30 32

31To 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.

32 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.

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

34 38

35In 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:

41 45

42```shell46```shell

43# Dedicated flag47# Dedicated flag

~~44codex --model gpt-5.2~~48codex --model gpt-5.4

45 49

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

~~47codex --config model='"gpt-5.2"'~~51codex --config model='"gpt-5.4"'

48codex --config sandbox_workspace_write.network_access=true52codex --config sandbox_workspace_write.network_access=true

49codex --config 'shell_environment_policy.include_only=["PATH","HOME"]'53codex --config 'shell_environment_policy.include_only=["PATH","HOME"]'

50```54```

70 74

71For 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).

72 76

73If 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.

74 78

75```toml79```toml

~~76export OPENAI_BASE_URL="https://api.openai.com/v1"~~80openai_base_url = "https://us.api.openai.com/v1"

~~77codex~~

78```81```

79 82

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

83 86

84For 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 `.codex/config.toml` files in the project.

85 88

~~86Relative paths inside a project config (for example, `experimental_instructions_file`) are resolved relative to the `.codex/` folder that contains the `config.toml`.~~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.

96In practice, the two most useful locations are:

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

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

100

101Turn hooks on with:

102

103```toml

104[features]

105codex_hooks = true

106```

107

108For the current event list, input fields, output behavior, and limitations, see

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

87 110

88## Agent roles (`[agents]` in `config.toml`)111## Agent roles (`[agents]` in `config.toml`)

89 112

~~90For multi-agent role configuration (`[agents]` in `config.toml`), see [Multi-agents](https://developers.openai.com/codex/multi-agent).~~113For subagent role configuration (`[agents]` in `config.toml`), see [Subagents](https://developers.openai.com/codex/subagents).

91 114

92## Project root detection115## Project root detection

93 116

104 127

105## Custom model providers128## Custom model providers

106 129

107A model provider defines how Codex connects to a model (base URL, wire API, and optional HTTP headers).130A 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`.

108 131

109Define additional providers and point `model_provider` at them:132Define additional providers and point `model_provider` at them:

110 133

111```toml134```toml

112model = "gpt-5.1"135model = "gpt-5.4"

113model_provider = "proxy"136model_provider = "proxy"

114 137

115[model_providers.proxy]138[model_providers.proxy]

117base_url = "http://proxy.example.com"140base_url = "http://proxy.example.com"

118env_key = "OPENAI_API_KEY"141env_key = "OPENAI_API_KEY"

119 142

120[model_providers.ollama]143[model_providers.local_ollama]

121name = "Ollama"144name = "Ollama"

122base_url = "http://localhost:11434/v1"145base_url = "http://localhost:11434/v1"

123 146

135env_http_headers = { "X-Example-Features" = "EXAMPLE_FEATURES" }158env_http_headers = { "X-Example-Features" = "EXAMPLE_FEATURES" }

136```159```

137 160

161Use command-backed authentication when a provider needs Codex to fetch bearer tokens from an external credential helper:

162

163```toml

164[model_providers.proxy]

165name = "OpenAI using LLM proxy"

166base_url = "https://proxy.example.com/v1"

167wire_api = "responses"

168

169[model_providers.proxy.auth]

170command = "/usr/local/bin/fetch-codex-token"

171args = ["--audience", "codex"]

172timeout_ms = 5000

173refresh_interval_ms = 300000

174```

175

176The 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`.

177

138## OSS mode (local providers)178## OSS mode (local providers)

139 179

140Codex 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.180Codex 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.

153env_key = "AZURE_OPENAI_API_KEY"193env_key = "AZURE_OPENAI_API_KEY"

154query_params = { api-version = "2025-04-01-preview" }194query_params = { api-version = "2025-04-01-preview" }

155wire_api = "responses"195wire_api = "responses"

~~156~~

157[model_providers.openai]

158request_max_retries = 4196request_max_retries = 4

159stream_max_retries = 10197stream_max_retries = 10

160stream_idle_timeout_ms = 300000198stream_idle_timeout_ms = 300000

161```199```

162 200

201To 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.

202

163## ChatGPT customers using data residency203## ChatGPT customers using data residency

164 204

165Projects 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).205Projects 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).

184 224

185## Approval policies and sandbox modes225## Approval policies and sandbox modes

186 226

187Pick 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.227Pick approval strictness (affects when Codex pauses) and sandbox level (affects file/network access).

228

229For 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).

230

231You 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.

188 232

189```233```

190approval_policy = "untrusted" # Other options: on-request, never234approval_policy = "untrusted" # Other options: on-request, never, or { granular = { ... } }

191sandbox_mode = "workspace-write"235sandbox_mode = "workspace-write"

236allow_login_shell = false # Optional hardening: disallow login shells for shell tools

237

238# Example granular approval policy:

239# approval_policy = { granular = {

240# sandbox_approval = true,

241# rules = true,

242# mcp_elicitations = true,

243# request_permissions = false,

244# skill_approval = false

245# } }

192 246

193[sandbox_workspace_write]247[sandbox_workspace_write]

194exclude_tmpdir_env_var = false # Allow $TMPDIR248exclude_tmpdir_env_var = false # Allow $TMPDIR

197network_access = false # Opt in to outbound network251network_access = false # Opt in to outbound network

198```252```

199 253

254Need 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).

255

200In workspace-write mode, some environments keep `.git/` and `.codex/`256In workspace-write mode, some environments keep `.git/` and `.codex/`

201 read-only even when the rest of the workspace is writable. This is why257 read-only even when the rest of the workspace is writable. This is why

202 commands like `git commit` may still require approval to run outside the258 commands like `git commit` may still require approval to run outside the

293 349

294For more security and privacy guidance around telemetry, see [Security](https://developers.openai.com/codex/security#monitoring-and-telemetry).350For more security and privacy guidance around telemetry, see [Security](https://developers.openai.com/codex/agent-approvals-security#monitoring-and-telemetry).

295 351

296### Metrics352### Metrics

297 353

config-advanced.md Codex Docs, 2026-02-19 20:37 UTC → 2026-04-15 06:44 UTC