config-advanced.md +104 −20
84 84
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.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.
86 86
8787For 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.For 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.
88 88
89Relative paths inside a project config (for example, `model_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`.
90 90
9191## Hooks (experimental)Project config files can't override settings that redirect credentials, change
92provider auth, or run machine-local notification/telemetry commands.
93Codex ignores the following keys in project-local `.codex/config.toml` and
94prints a startup warning when it sees them: `openai_base_url`,
95`chatgpt_base_url`, `model_provider`, `model_providers`, `notify`, `profile`,
96`profiles`, `experimental_realtime_ws_base_url`, and `otel`. Set those keys in
97your user-level `~/.codex/config.toml` instead.
92 98
9399Codex can also load lifecycle hooks from `hooks.json` files that sit next to## Hooks
94active config layers.
95 100
96101In practice, the two most useful locations are:Codex can also load lifecycle hooks from either `hooks.json` files or inline
102`[hooks]` tables in `config.toml` files that sit next to active config layers.
103
104In practice, the four most useful locations are:
97 105
98- `~/.codex/hooks.json`106- `~/.codex/hooks.json`
107- `~/.codex/config.toml`
99- `<repo>/.codex/hooks.json`108- `<repo>/.codex/hooks.json`
109- `<repo>/.codex/config.toml`
110
111Project-local hooks load only when the project `.codex/` layer is trusted.
112User-level hooks remain independent of project trust.
100 113
101114Turn hooks on with:Inline TOML hooks use the same event structure as `hooks.json`:
102 115
103```toml116```toml
104117[features][[hooks.PreToolUse]]
105118codex_hooks = truematcher = "^Bash$"
119
120[[hooks.PreToolUse.hooks]]
121type = "command"
122command = '/usr/bin/python3 "$(git rev-parse --show-toplevel)/.codex/hooks/pre_tool_use_policy.py"'
123timeout = 30
124statusMessage = "Checking Bash command"
106```125```
107 126
127If a single layer contains both `hooks.json` and inline `[hooks]`, Codex loads
128both and warns. Prefer one representation per layer.
129
108For the current event list, input fields, output behavior, and limitations, see130For the current event list, input fields, output behavior, and limitations, see
109[Hooks](https://developers.openai.com/codex/hooks).131[Hooks](https://developers.openai.com/codex/hooks).
110 132
175 197
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`.198The 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`.
177 199
200### Amazon Bedrock provider
201
202Codex includes a built-in `amazon-bedrock` model provider. Set it directly as
203`model_provider`; unlike custom providers, this built-in provider supports only
204the nested AWS profile and region overrides.
205
206```toml
207model_provider = "amazon-bedrock"
208model = "<bedrock-model-id>"
209
210[model_providers.amazon-bedrock.aws]
211profile = "default"
212region = "eu-central-1"
213```
214
215If you omit `profile`, Codex uses the standard AWS credential chain. Set
216`region` to the supported Bedrock region that should handle requests.
217
178## OSS mode (local providers)218## OSS mode (local providers)
179 219
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.220Codex 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.
230 270
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.271You 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.
232 272
233273```Set `approvals_reviewer = "auto_review"` to route eligible interactive approval
274requests through automatic review. This changes the reviewer, not the sandbox
275boundary.
276
277Use `[auto_review].policy` for local reviewer policy instructions. Managed
278`guardian_policy_config` takes precedence.
279
280```toml
234approval_policy = "untrusted" # Other options: on-request, never, or { granular = { ... } }281approval_policy = "untrusted" # Other options: on-request, never, or { granular = { ... } }
282approvals_reviewer = "user" # Or "auto_review" for automatic review
235sandbox_mode = "workspace-write"283sandbox_mode = "workspace-write"
236allow_login_shell = false # Optional hardening: disallow login shells for shell tools284allow_login_shell = false # Optional hardening: disallow login shells for shell tools
237 285
249exclude_slash_tmp = false # Allow /tmp297exclude_slash_tmp = false # Allow /tmp
250writable_roots = ["/Users/YOU/.pyenv/shims"]298writable_roots = ["/Users/YOU/.pyenv/shims"]
251network_access = false # Opt in to outbound network299network_access = false # Opt in to outbound network
300
301[auto_review]
302policy = """
303Use your organization's automatic review policy.
304"""
305```
306
307### Named permission profiles
308
309Set `default_permissions` to reuse a sandbox profile by name. Codex includes
310the built-in profiles `:read-only`, `:workspace`, and `:danger-no-sandbox`:
311
312```toml
313default_permissions = ":workspace"
314```
315
316For custom profiles, point `default_permissions` at a name you define under
317`[permissions.<name>]`:
318
319```toml
320default_permissions = "workspace"
321
322[permissions.workspace.filesystem]
323":project_roots" = { "." = "write", "**/*.env" = "none" }
324glob_scan_max_depth = 3
325
326[permissions.workspace.network]
327enabled = true
328mode = "limited"
329
330[permissions.workspace.network.domains]
331"api.openai.com" = "allow"
252```332```
253 333
334Use built-in names with a leading colon. Custom names don't use a leading
335colon and must have matching `permissions` tables.
336
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).337Need 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).
255 338
256In workspace-write mode, some environments keep `.git/` and `.codex/`339In workspace-write mode, some environments keep `.git/` and `.codex/`
257 read-only even when the rest of the workspace is writable. This is why340 read-only even when the rest of the workspace is writable. This is why
258 commands like `git commit` may still require approval to run outside the341 commands like `git commit` may still require approval to run outside the
259342sandbox. If you want Codex to skip specific commands (for example, block `git commit` outside the sandbox), use sandbox. If you want Codex to skip specific commands (for example, block `git
260343[rules](https://developers.openai.com/codex/rules). commit` outside the sandbox), use
344 <a href="/codex/rules">rules</a>.
261 345
262Disable sandboxing entirely (use only if your environment already isolates processes):346Disable sandboxing entirely (use only if your environment already isolates processes):
263 347
335Each metric below also includes default metadata tags: `auth_mode`, `originator`, `session_source`, `model`, and `app.version`.419Each metric below also includes default metadata tags: `auth_mode`, `originator`, `session_source`, `model`, and `app.version`.
336 420
337| Metric | Type | Fields | Description |421| Metric | Type | Fields | Description |
338422| --- | --- | --- | --- || ------------------------------------- | --------- | ------------------- | ----------------------------------------------------------------- |
339| `codex.api_request` | counter | `status`, `success` | API request count by HTTP status and success/failure. |423| `codex.api_request` | counter | `status`, `success` | API request count by HTTP status and success/failure. |
340| `codex.api_request.duration_ms` | histogram | `status`, `success` | API request duration in milliseconds. |424| `codex.api_request.duration_ms` | histogram | `status`, `success` | API request duration in milliseconds. |
341| `codex.sse_event` | counter | `kind`, `success` | SSE event count by event kind and success/failure. |425| `codex.sse_event` | counter | `kind`, `success` | SSE event count by event kind and success/failure. |
377#### Runtime and model transport461#### Runtime and model transport
378 462
379| Metric | Type | Fields | Description |463| Metric | Type | Fields | Description |
380464| --- | --- | --- | --- || ----------------------------------------------- | --------- | -------------------- | ------------------------------------------------------------ |
381| `api_request` | counter | `status`, `success` | API request count by HTTP status and success/failure. |465| `api_request` | counter | `status`, `success` | API request count by HTTP status and success/failure. |
382| `api_request.duration_ms` | histogram | `status`, `success` | API request duration in milliseconds. |466| `api_request.duration_ms` | histogram | `status`, `success` | API request duration in milliseconds. |
383| `sse_event` | counter | `kind`, `success` | SSE event count by event kind and success/failure. |467| `sse_event` | counter | `kind`, `success` | SSE event count by event kind and success/failure. |
386| `websocket.request.duration_ms` | histogram | `success` | WebSocket request duration in milliseconds. |470| `websocket.request.duration_ms` | histogram | `success` | WebSocket request duration in milliseconds. |
387| `websocket.event` | counter | `kind`, `success` | WebSocket message/event count by type and success/failure. |471| `websocket.event` | counter | `kind`, `success` | WebSocket message/event count by type and success/failure. |
388| `websocket.event.duration_ms` | histogram | `kind`, `success` | WebSocket message/event processing duration in milliseconds. |472| `websocket.event.duration_ms` | histogram | `kind`, `success` | WebSocket message/event processing duration in milliseconds. |
389473| `responses_api_overhead.duration_ms` | histogram | | Responses API overhead timing from websocket responses. || `responses_api_overhead.duration_ms` | histogram | | Responses API overhead timing from WebSocket responses. |
390474| `responses_api_inference_time.duration_ms` | histogram | | Responses API inference timing from websocket responses. || `responses_api_inference_time.duration_ms` | histogram | | Responses API inference timing from WebSocket responses. |
391| `responses_api_engine_iapi_ttft.duration_ms` | histogram | | Responses API engine IAPI time-to-first-token timing. |475| `responses_api_engine_iapi_ttft.duration_ms` | histogram | | Responses API engine IAPI time-to-first-token timing. |
392| `responses_api_engine_service_ttft.duration_ms` | histogram | | Responses API engine service time-to-first-token timing. |476| `responses_api_engine_service_ttft.duration_ms` | histogram | | Responses API engine service time-to-first-token timing. |
393| `responses_api_engine_iapi_tbt.duration_ms` | histogram | | Responses API engine IAPI time-between-token timing. |477| `responses_api_engine_iapi_tbt.duration_ms` | histogram | | Responses API engine IAPI time-between-token timing. |
407#### Turn and tool activity491#### Turn and tool activity
408 492
409| Metric | Type | Fields | Description |493| Metric | Type | Fields | Description |
410494| --- | --- | --- | --- || -------------------------------------- | --------- | ------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- |
411| `turn.e2e_duration_ms` | histogram | | End-to-end time for a full turn. |495| `turn.e2e_duration_ms` | histogram | | End-to-end time for a full turn. |
412| `turn.ttft.duration_ms` | histogram | | Time to first token for a turn. |496| `turn.ttft.duration_ms` | histogram | | Time to first token for a turn. |
413| `turn.ttfm.duration_ms` | histogram | | Time to first model output item for a turn. |497| `turn.ttfm.duration_ms` | histogram | | Time to first model output item for a turn. |
422| `mcp.call` | counter | See note | MCP tool invocation result. |506| `mcp.call` | counter | See note | MCP tool invocation result. |
423| `mcp.call.duration_ms` | histogram | See note | MCP tool invocation duration. |507| `mcp.call.duration_ms` | histogram | See note | MCP tool invocation duration. |
424| `mcp.tools.list.duration_ms` | histogram | `cache` | MCP tool-list duration, including cache hit/miss state. |508| `mcp.tools.list.duration_ms` | histogram | `cache` | MCP tool-list duration, including cache hit/miss state. |
425509| `mcp.tools.fetch_uncached.duration_ms` | histogram | | Duration of uncached MCP tool fetches. || `mcp.tools.fetch_uncached.duration_ms` | histogram | | Duration of MCP tool fetches that miss the cache. |
426| `mcp.tools.cache_write.duration_ms` | histogram | | Duration of Codex Apps MCP tool-cache writes. |510| `mcp.tools.cache_write.duration_ms` | histogram | | Duration of Codex Apps MCP tool-cache writes. |
427| `hooks.run` | counter | `hook_name`, `source`, `status` | Hook run count by hook name, source, and status. |511| `hooks.run` | counter | `hook_name`, `source`, `status` | Hook run count by hook name, source, and status. |
428| `hooks.run.duration_ms` | histogram | `hook_name`, `source`, `status` | Hook run duration in milliseconds. |512| `hooks.run.duration_ms` | histogram | `hook_name`, `source`, `status` | Hook run duration in milliseconds. |
432#### Threads, tasks, and features516#### Threads, tasks, and features
433 517
434| Metric | Type | Fields | Description |518| Metric | Type | Fields | Description |
435519| --- | --- | --- | --- || --------------------------------- | --------- | --------------------- | -------------------------------------------------------------------------------- |
436| `feature.state` | counter | `feature`, `value` | Feature values that differ from defaults (emit one row per non-default). |520| `feature.state` | counter | `feature`, `value` | Feature values that differ from defaults (emit one row per non-default). |
437| `status_line` | counter | | Session started with a configured status line. |521| `status_line` | counter | | Session started with a configured status line. |
438| `model_warning` | counter | | Warning sent to the model. |522| `model_warning` | counter | | Warning sent to the model. |
462#### Memory and local state546#### Memory and local state
463 547
464| Metric | Type | Fields | Description |548| Metric | Type | Fields | Description |
465549| --- | --- | --- | --- || ------------------------------ | --------- | ------------------------- | --------------------------------------------------------- |
466| `memory.phase1` | counter | `status` | Memory phase 1 job counts by status. |550| `memory.phase1` | counter | `status` | Memory phase 1 job counts by status. |
467| `memory.phase1.e2e_ms` | histogram | | End-to-end duration for memory phase 1. |551| `memory.phase1.e2e_ms` | histogram | | End-to-end duration for memory phase 1. |
468| `memory.phase1.output` | counter | | Memory phase 1 outputs written. |552| `memory.phase1.output` | counter | | Memory phase 1 outputs written. |
483#### Windows sandbox567#### Windows sandbox
484 568
485| Metric | Type | Fields | Description |569| Metric | Type | Fields | Description |
486570| --- | --- | --- | --- || ------------------------------------------------ | --------- | ----------------------------------------- | ----------------------------------------------------- |
487| `windows_sandbox.setup_success` | counter | `originator`, `mode` | Windows sandbox setup successes. |571| `windows_sandbox.setup_success` | counter | `originator`, `mode` | Windows sandbox setup successes. |
488| `windows_sandbox.setup_failure` | counter | `originator`, `mode` | Windows sandbox setup failures. |572| `windows_sandbox.setup_failure` | counter | `originator`, `mode` | Windows sandbox setup failures. |
489| `windows_sandbox.setup_duration_ms` | histogram | `result`, `originator`, `mode` | Windows sandbox setup duration. |573| `windows_sandbox.setup_duration_ms` | histogram | `result`, `originator`, `mode` | Windows sandbox setup duration. |