config-reference.md Codex Docs, 2026-03-05 00:34 UTC → 2026-04-29 12:40 UTC

6 6 

7User-level configuration lives in `~/.codex/config.toml`. You can also add project-scoped overrides in `.codex/config.toml` files. Codex loads project-scoped config files only when you trust the project.7User-level configuration lives in `~/.codex/config.toml`. You can also add project-scoped overrides in `.codex/config.toml` files. Codex loads project-scoped config files only when you trust the project.

8 8 

9For sandbox and approval keys (`approval_policy`, `sandbox_mode`, and `sandbox_workspace_write.*`), pair this reference with [Sandbox and approvals](https://developers.openai.com/codex/security#sandbox-and-approvals), [Protected paths in writable roots](https://developers.openai.com/codex/security#protected-paths-in-writable-roots), and [Network access](https://developers.openai.com/codex/security#network-access).9For sandbox and approval keys (`approval_policy`, `sandbox_mode`, and `sandbox_workspace_write.*`), pair this reference with [Sandbox and approvals](https://developers.openai.com/codex/agent-approvals-security#sandbox-and-approvals), [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).

10 10 

11| Key | Type / Values | Details |11| Key | Type / Values | Details |

12| --- | --- | --- |12| --- | --- | --- |

13| `agents.<name>.config_file` | `string (path)` | Path to a TOML config layer for that role; relative paths resolve from the config file that declares the role. |13| `agents.<name>.config_file` | `string (path)` | Path to a TOML config layer for that role; relative paths resolve from the config file that declares the role. |

14| `agents.<name>.description` | `string` | Role guidance shown to Codex when choosing and spawning that agent type. |14| `agents.<name>.description` | `string` | Role guidance shown to Codex when choosing and spawning that agent type. |

15| `agents.<name>.nickname_candidates` | `array<string>` | Optional pool of display nicknames for spawned agents in that role. |

15| `agents.job_max_runtime_seconds` | `number` | Default per-worker timeout for `spawn_agents_on_csv` jobs. When unset, the tool falls back to 1800 seconds per worker. |16| `agents.job_max_runtime_seconds` | `number` | Default per-worker timeout for `spawn_agents_on_csv` jobs. When unset, the tool falls back to 1800 seconds per worker. |

16| `agents.max_depth` | `number` | Maximum nesting depth allowed for spawned agent threads (root sessions start at depth 0; default: 1). |17| `agents.max_depth` | `number` | Maximum nesting depth allowed for spawned agent threads (root sessions start at depth 0; default: 1). |

17| `agents.max_threads` | `number` | Maximum number of agent threads that can be open concurrently. |18| `agents.max_threads` | `number` | Maximum number of agent threads that can be open concurrently. Defaults to `6` when unset. |

18| `allow_login_shell` | `boolean` | Allow shell-based tools to use login-shell semantics. Defaults to `true`; when `false`, `login = true` requests are rejected and omitted `login` defaults to non-login shells. |19| `allow_login_shell` | `boolean` | Allow shell-based tools to use login-shell semantics. Defaults to `true`; when `false`, `login = true` requests are rejected and omitted `login` defaults to non-login shells. |

19| `approval_policy` | `untrusted | on-request | never | { reject = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool } }` | Controls when Codex pauses for approval before executing commands. You can also use `approval_policy = { reject = { ... } }` to auto-reject specific prompt categories while keeping other prompts interactive. `on-failure` is deprecated; use `on-request` for interactive runs or `never` for non-interactive runs. |20| `analytics.enabled` | `boolean` | Enable or disable analytics for this machine/profile. When unset, the client default applies. |

20| `approval_policy.reject.mcp_elicitations` | `boolean` | When `true`, MCP elicitation prompts are auto-rejected instead of shown to the user. |21| `approval_policy` | `untrusted | on-request | never | { granular = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool, request_permissions = bool, skill_approval = bool } }` | Controls when Codex pauses for approval before executing commands. You can also use `approval_policy = { granular = { ... } }` to allow or auto-reject specific prompt categories while keeping other prompts interactive. `on-failure` is deprecated; use `on-request` for interactive runs or `never` for non-interactive runs. |

21| `approval_policy.reject.rules` | `boolean` | When `true`, approvals triggered by execpolicy `prompt` rules are auto-rejected. |22| `approval_policy.granular.mcp_elicitations` | `boolean` | When `true`, MCP elicitation prompts are allowed to surface instead of being auto-rejected. |

22| `approval_policy.reject.sandbox_approval` | `boolean` | When `true`, sandbox escalation approval prompts are auto-rejected. |23| `approval_policy.granular.request_permissions` | `boolean` | When `true`, prompts from the `request_permissions` tool are allowed to surface. |

24| `approval_policy.granular.rules` | `boolean` | When `true`, approvals triggered by execpolicy `prompt` rules are allowed to surface. |

25| `approval_policy.granular.sandbox_approval` | `boolean` | When `true`, sandbox escalation approval prompts are allowed to surface. |

26| `approval_policy.granular.skill_approval` | `boolean` | When `true`, skill-script approval prompts are allowed to surface. |

27| `approvals_reviewer` | `user | auto_review` | Who reviews eligible approval prompts under `on-request` or granular approval policies. Defaults to `user`; `auto_review` uses the reviewer subagent. This setting doesn't change sandboxing or review actions already allowed inside the sandbox. |

23| `apps._default.destructive_enabled` | `boolean` | Default allow/deny for app tools with `destructive_hint = true`. |28| `apps._default.destructive_enabled` | `boolean` | Default allow/deny for app tools with `destructive_hint = true`. |

24| `apps._default.enabled` | `boolean` | Default app enabled state for all apps unless overridden per app. |29| `apps._default.enabled` | `boolean` | Default app enabled state for all apps unless overridden per app. |

25| `apps._default.open_world_enabled` | `boolean` | Default allow/deny for app tools with `open_world_hint = true`. |30| `apps._default.open_world_enabled` | `boolean` | Default allow/deny for app tools with `open_world_hint = true`. |

30| `apps.<id>.open_world_enabled` | `boolean` | Allow or block tools in this app that advertise `open_world_hint = true`. |35| `apps.<id>.open_world_enabled` | `boolean` | Allow or block tools in this app that advertise `open_world_hint = true`. |

31| `apps.<id>.tools.<tool>.approval_mode` | `auto | prompt | approve` | Per-tool approval behavior override for a single app tool. |36| `apps.<id>.tools.<tool>.approval_mode` | `auto | prompt | approve` | Per-tool approval behavior override for a single app tool. |

32| `apps.<id>.tools.<tool>.enabled` | `boolean` | Per-tool enabled override for an app tool (for example `repos/list`). |37| `apps.<id>.tools.<tool>.enabled` | `boolean` | Per-tool enabled override for an app tool (for example `repos/list`). |

38| `auto_review.policy` | `string` | Local Markdown policy instructions for automatic review. Managed `guardian_policy_config` takes precedence. Blank values are ignored. |

33| `background_terminal_max_timeout` | `number` | Maximum poll window in milliseconds for empty `write_stdin` polls (background terminal polling). Default: `300000` (5 minutes). Replaces the older `background_terminal_timeout` key. |39| `background_terminal_max_timeout` | `number` | Maximum poll window in milliseconds for empty `write_stdin` polls (background terminal polling). Default: `300000` (5 minutes). Replaces the older `background_terminal_timeout` key. |

34| `chatgpt_base_url` | `string` | Override the base URL used during the ChatGPT login flow. |40| `chatgpt_base_url` | `string` | Override the base URL used during the ChatGPT login flow. |

35| `check_for_update_on_startup` | `boolean` | Check for Codex updates on startup (set to false only when updates are centrally managed). |41| `check_for_update_on_startup` | `boolean` | Check for Codex updates on startup (set to false only when updates are centrally managed). |

36| `cli_auth_credentials_store` | `file | keyring | auto` | Control where the CLI stores cached credentials (file-based auth.json vs OS keychain). |42| `cli_auth_credentials_store` | `file | keyring | auto` | Control where the CLI stores cached credentials (file-based auth.json vs OS keychain). |

43| `commit_attribution` | `string` | Override the commit co-author trailer text. Set an empty string to disable automatic attribution. |

37| `compact_prompt` | `string` | Inline override for the history compaction prompt. |44| `compact_prompt` | `string` | Inline override for the history compaction prompt. |

45| `default_permissions` | `string` | Name of the default permissions profile to apply to sandboxed tool calls. |

38| `developer_instructions` | `string` | Additional developer instructions injected into the session (optional). |46| `developer_instructions` | `string` | Additional developer instructions injected into the session (optional). |

39| `disable_paste_burst` | `boolean` | Disable burst-paste detection in the TUI. |47| `disable_paste_burst` | `boolean` | Disable burst-paste detection in the TUI. |

40| `experimental_compact_prompt_file` | `string (path)` | Load the compaction prompt override from a file (experimental). |48| `experimental_compact_prompt_file` | `string (path)` | Load the compaction prompt override from a file (experimental). |

41| `experimental_use_freeform_apply_patch` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform` or `codex --enable apply_patch_freeform`. |

42| `experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`. |49| `experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`. |

43| `features.apply_patch_freeform` | `boolean` | Expose the freeform `apply_patch` tool (experimental). |

44| `features.apps` | `boolean` | Enable ChatGPT Apps/connectors support (experimental). |50| `features.apps` | `boolean` | Enable ChatGPT Apps/connectors support (experimental). |

45| `features.apps_mcp_gateway` | `boolean` | Route Apps MCP calls through the OpenAI connectors MCP gateway (`https://api.openai.com/v1/connectors/mcp/`) instead of legacy routing (experimental). |51| `features.codex_hooks` | `boolean` | Enable lifecycle hooks loaded from `hooks.json` or inline `[hooks]` config. |

46| `features.child_agents_md` | `boolean` | Append AGENTS.md scope/precedence guidance even when no AGENTS.md is present (experimental). |52| `features.enable_request_compression` | `boolean` | Compress streaming request bodies with zstd when supported (stable; on by default). |

47| `features.collaboration_modes` | `boolean` | Enable collaboration modes such as plan mode (stable; on by default). |53| `features.fast_mode` | `boolean` | Enable Fast mode selection and the `service_tier = "fast"` path (stable; on by default). |

48| `features.multi_agent` | `boolean` | Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait`, `close_agent`, and `spawn_agents_on_csv`) (experimental; off by default). |54| `features.memories` | `boolean` | Enable [Memories](https://developers.openai.com/codex/memories) (off by default). |

55| `features.multi_agent` | `boolean` | Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait_agent`, and `close_agent`) (stable; on by default). |

49| `features.personality` | `boolean` | Enable personality selection controls (stable; on by default). |56| `features.personality` | `boolean` | Enable personality selection controls (stable; on by default). |

50| `features.powershell_utf8` | `boolean` | Force PowerShell UTF-8 output (defaults to true). |57| `features.prevent_idle_sleep` | `boolean` | Prevent the machine from sleeping while a turn is actively running (experimental; off by default). |

51| `features.remote_models` | `boolean` | Refresh remote model list before showing readiness (experimental). |58| `features.shell_snapshot` | `boolean` | Snapshot shell environment to speed up repeated commands (stable; on by default). |

52| `features.request_rule` | `boolean` | Enable Smart approvals (`prefix_rule` suggestions on escalation requests; stable; on by default). |

53| `features.runtime_metrics` | `boolean` | Show runtime metrics summary in TUI turn separators (experimental). |

54| `features.search_tool` | `boolean` | Enable `search_tool_bm25` for Apps tool discovery before invoking app MCP tools (experimental). |

55| `features.shell_snapshot` | `boolean` | Snapshot shell environment to speed up repeated commands (beta). |

56| `features.shell_tool` | `boolean` | Enable the default `shell` tool for running commands (stable; on by default). |59| `features.shell_tool` | `boolean` | Enable the default `shell` tool for running commands (stable; on by default). |

57| `features.unified_exec` | `boolean` | Use the unified PTY-backed exec tool (beta). |60| `features.skill_mcp_dependency_install` | `boolean` | Allow prompting and installing missing MCP dependencies for skills (stable; on by default). |

58| `features.use_linux_sandbox_bwrap` | `boolean` | Use the bubblewrap-based Linux sandbox pipeline (experimental; off by default). |61| `features.undo` | `boolean` | Enable undo support (stable; off by default). |

62| `features.unified_exec` | `boolean` | Use the unified PTY-backed exec tool (stable; enabled by default except on Windows). |

59| `features.web_search` | `boolean` | Deprecated legacy toggle; prefer the top-level `web_search` setting. |63| `features.web_search` | `boolean` | Deprecated legacy toggle; prefer the top-level `web_search` setting. |

60| `features.web_search_cached` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "cached"`. |64| `features.web_search_cached` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "cached"`. |

61| `features.web_search_request` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "live"`. |65| `features.web_search_request` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "live"`. |

66| `hide_agent_reasoning` | `boolean` | Suppress reasoning events in both the TUI and `codex exec` output. |70| `hide_agent_reasoning` | `boolean` | Suppress reasoning events in both the TUI and `codex exec` output. |

67| `history.max_bytes` | `number` | If set, caps the history file size in bytes by dropping oldest entries. |71| `history.max_bytes` | `number` | If set, caps the history file size in bytes by dropping oldest entries. |

68| `history.persistence` | `save-all | none` | Control whether Codex saves session transcripts to history.jsonl. |72| `history.persistence` | `save-all | none` | Control whether Codex saves session transcripts to history.jsonl. |

69| `include_apply_patch_tool` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`. |73| `hooks` | `table` | Lifecycle hooks configured inline in `config.toml`. Uses the same event schema as `hooks.json`; see the Hooks guide for examples and supported events. |

70| `instructions` | `string` | Reserved for future use; prefer `model_instructions_file` or `AGENTS.md`. |74| `instructions` | `string` | Reserved for future use; prefer `model_instructions_file` or `AGENTS.md`. |

71| `log_dir` | `string (path)` | Directory where Codex writes log files (for example `codex-tui.log`); defaults to `$CODEX_HOME/log`. |75| `log_dir` | `string (path)` | Directory where Codex writes log files (for example `codex-tui.log`); defaults to `$CODEX_HOME/log`. |

72| `mcp_oauth_callback_port` | `integer` | Optional fixed port for the local HTTP callback server used during MCP OAuth login. When unset, Codex binds to an ephemeral port chosen by the OS. |76| `mcp_oauth_callback_port` | `integer` | Optional fixed port for the local HTTP callback server used during MCP OAuth login. When unset, Codex binds to an ephemeral port chosen by the OS. |

81| `mcp_servers.<id>.enabled_tools` | `array<string>` | Allow list of tool names exposed by the MCP server. |85| `mcp_servers.<id>.enabled_tools` | `array<string>` | Allow list of tool names exposed by the MCP server. |

82| `mcp_servers.<id>.env` | `map<string,string>` | Environment variables forwarded to the MCP stdio server. |86| `mcp_servers.<id>.env` | `map<string,string>` | Environment variables forwarded to the MCP stdio server. |

83| `mcp_servers.<id>.env_http_headers` | `map<string,string>` | HTTP headers populated from environment variables for an MCP HTTP server. |87| `mcp_servers.<id>.env_http_headers` | `map<string,string>` | HTTP headers populated from environment variables for an MCP HTTP server. |

84| `mcp_servers.<id>.env_vars` | `array<string>` | Additional environment variables to whitelist for an MCP stdio server. |88| `mcp_servers.<id>.env_vars` | `array<string | { name = string, source = "local" | "remote" }>` | Additional environment variables to whitelist for an MCP stdio server. String entries default to `source = "local"`; use `source = "remote"` only with executor-backed remote stdio. |

89| `mcp_servers.<id>.experimental_environment` | `local | remote` | Experimental placement for an MCP server. `remote` starts stdio servers through a remote executor environment; streamable HTTP remote placement is not implemented. |

85| `mcp_servers.<id>.http_headers` | `map<string,string>` | Static HTTP headers included with each MCP HTTP request. |90| `mcp_servers.<id>.http_headers` | `map<string,string>` | Static HTTP headers included with each MCP HTTP request. |

91| `mcp_servers.<id>.oauth_resource` | `string` | Optional RFC 8707 OAuth resource parameter to include during MCP login. |

86| `mcp_servers.<id>.required` | `boolean` | When true, fail startup/resume if this enabled MCP server cannot initialize. |92| `mcp_servers.<id>.required` | `boolean` | When true, fail startup/resume if this enabled MCP server cannot initialize. |

93| `mcp_servers.<id>.scopes` | `array<string>` | OAuth scopes to request when authenticating to that MCP server. |

87| `mcp_servers.<id>.startup_timeout_ms` | `number` | Alias for `startup_timeout_sec` in milliseconds. |94| `mcp_servers.<id>.startup_timeout_ms` | `number` | Alias for `startup_timeout_sec` in milliseconds. |

88| `mcp_servers.<id>.startup_timeout_sec` | `number` | Override the default 10s startup timeout for an MCP server. |95| `mcp_servers.<id>.startup_timeout_sec` | `number` | Override the default 10s startup timeout for an MCP server. |

89| `mcp_servers.<id>.tool_timeout_sec` | `number` | Override the default 60s per-tool timeout for an MCP server. |96| `mcp_servers.<id>.tool_timeout_sec` | `number` | Override the default 60s per-tool timeout for an MCP server. |

90| `mcp_servers.<id>.url` | `string` | Endpoint for an MCP streamable HTTP server. |97| `mcp_servers.<id>.url` | `string` | Endpoint for an MCP streamable HTTP server. |

91| `model` | `string` | Model to use (e.g., `gpt-5-codex`). |98| `memories.consolidation_model` | `string` | Optional model override for global memory consolidation. |

99| `memories.disable_on_external_context` | `boolean` | When `true`, threads that use external context such as MCP tool calls, web search, or tool search are kept out of memory generation. Defaults to `false`. Legacy alias: `memories.no_memories_if_mcp_or_web_search`. |

100| `memories.extract_model` | `string` | Optional model override for per-thread memory extraction. |

101| `memories.generate_memories` | `boolean` | When `false`, newly created threads are not stored as memory-generation inputs. Defaults to `true`. |

102| `memories.max_raw_memories_for_consolidation` | `number` | Maximum recent raw memories retained for global consolidation. Defaults to `256` and is capped at `4096`. |

103| `memories.max_rollout_age_days` | `number` | Maximum age of threads considered for memory generation. Defaults to `30` and is clamped to `0`-`90`. |

104| `memories.max_rollouts_per_startup` | `number` | Maximum rollout candidates processed per startup pass. Defaults to `16` and is capped at `128`. |

105| `memories.max_unused_days` | `number` | Maximum days since a memory was last used before it becomes ineligible for consolidation. Defaults to `30` and is clamped to `0`-`365`. |

106| `memories.min_rate_limit_remaining_percent` | `number` | Minimum remaining percentage required in Codex rate-limit windows before memory generation starts. Defaults to `25` and is clamped to `0`-`100`. |

107| `memories.min_rollout_idle_hours` | `number` | Minimum idle time before a thread is considered for memory generation. Defaults to `6` and is clamped to `1`-`48`. |

108| `memories.use_memories` | `boolean` | When `false`, Codex skips injecting existing memories into future sessions. Defaults to `true`. |

109| `model` | `string` | Model to use (e.g., `gpt-5.5`). |

92| `model_auto_compact_token_limit` | `number` | Token threshold that triggers automatic history compaction (unset uses model defaults). |110| `model_auto_compact_token_limit` | `number` | Token threshold that triggers automatic history compaction (unset uses model defaults). |

93| `model_catalog_json` | `string (path)` | Optional path to a JSON model catalog loaded on startup. Profile-level `profiles.<name>.model_catalog_json` can override this per profile. |111| `model_catalog_json` | `string (path)` | Optional path to a JSON model catalog loaded on startup. Profile-level `profiles.<name>.model_catalog_json` can override this per profile. |

94| `model_context_window` | `number` | Context window tokens available to the active model. |112| `model_context_window` | `number` | Context window tokens available to the active model. |

95| `model_instructions_file` | `string (path)` | Replacement for built-in instructions instead of `AGENTS.md`. |113| `model_instructions_file` | `string (path)` | Replacement for built-in instructions instead of `AGENTS.md`. |

96| `model_provider` | `string` | Provider id from `model_providers` (default: `openai`). |114| `model_provider` | `string` | Provider id from `model_providers` (default: `openai`). |

115| `model_providers.<id>` | `table` | Custom provider definition. Built-in provider IDs (`openai`, `ollama`, and `lmstudio`) are reserved and cannot be overridden. |

116| `model_providers.<id>.auth` | `table` | Command-backed bearer token configuration for a custom provider. Do not combine with `env_key`, `experimental_bearer_token`, or `requires_openai_auth`. |

117| `model_providers.<id>.auth.args` | `array<string>` | Arguments passed to the token command. |

118| `model_providers.<id>.auth.command` | `string` | Command to run when Codex needs a bearer token. The command must print the token to stdout. |

119| `model_providers.<id>.auth.cwd` | `string (path)` | Working directory for the token command. |

120| `model_providers.<id>.auth.refresh_interval_ms` | `number` | How often Codex proactively refreshes the token in milliseconds (default: 300000). Set to `0` to refresh only after an authentication retry. |

121| `model_providers.<id>.auth.timeout_ms` | `number` | Maximum token command runtime in milliseconds (default: 5000). |

97| `model_providers.<id>.base_url` | `string` | API base URL for the model provider. |122| `model_providers.<id>.base_url` | `string` | API base URL for the model provider. |

98| `model_providers.<id>.env_http_headers` | `map<string,string>` | HTTP headers populated from environment variables when present. |123| `model_providers.<id>.env_http_headers` | `map<string,string>` | HTTP headers populated from environment variables when present. |

99| `model_providers.<id>.env_key` | `string` | Environment variable supplying the provider API key. |124| `model_providers.<id>.env_key` | `string` | Environment variable supplying the provider API key. |

106| `model_providers.<id>.requires_openai_auth` | `boolean` | The provider uses OpenAI authentication (defaults to false). |131| `model_providers.<id>.requires_openai_auth` | `boolean` | The provider uses OpenAI authentication (defaults to false). |

107| `model_providers.<id>.stream_idle_timeout_ms` | `number` | Idle timeout for SSE streams in milliseconds (default: 300000). |132| `model_providers.<id>.stream_idle_timeout_ms` | `number` | Idle timeout for SSE streams in milliseconds (default: 300000). |

108| `model_providers.<id>.stream_max_retries` | `number` | Retry count for SSE streaming interruptions (default: 5). |133| `model_providers.<id>.stream_max_retries` | `number` | Retry count for SSE streaming interruptions (default: 5). |

109| `model_providers.<id>.wire_api` | `chat | responses` | Protocol used by the provider (defaults to `chat` if omitted). |134| `model_providers.<id>.supports_websockets` | `boolean` | Whether that provider supports the Responses API WebSocket transport. |

135| `model_providers.<id>.wire_api` | `responses` | Protocol used by the provider. `responses` is the only supported value, and it is the default when omitted. |

110| `model_reasoning_effort` | `minimal | low | medium | high | xhigh` | Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent). |136| `model_reasoning_effort` | `minimal | low | medium | high | xhigh` | Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent). |

111| `model_reasoning_summary` | `auto | concise | detailed | none` | Select reasoning summary detail or disable summaries entirely. |137| `model_reasoning_summary` | `auto | concise | detailed | none` | Select reasoning summary detail or disable summaries entirely. |

112| `model_supports_reasoning_summaries` | `boolean` | Force Codex to send or not send reasoning metadata. |138| `model_supports_reasoning_summaries` | `boolean` | Force Codex to send or not send reasoning metadata. |

113| `model_verbosity` | `low | medium | high` | Control GPT-5 Responses API verbosity (defaults to `medium`). |139| `model_verbosity` | `low | medium | high` | Optional GPT-5 Responses API verbosity override; when unset, the selected model/preset default is used. |

114| `notice.hide_full_access_warning` | `boolean` | Track acknowledgement of the full access warning prompt. |140| `notice.hide_full_access_warning` | `boolean` | Track acknowledgement of the full access warning prompt. |

115| `notice.hide_gpt-5.1-codex-max_migration_prompt` | `boolean` | Track acknowledgement of the gpt-5.1-codex-max migration prompt. |141| `notice.hide_gpt-5.1-codex-max_migration_prompt` | `boolean` | Track acknowledgement of the gpt-5.1-codex-max migration prompt. |

116| `notice.hide_gpt5_1_migration_prompt` | `boolean` | Track acknowledgement of the GPT-5.1 migration prompt. |142| `notice.hide_gpt5_1_migration_prompt` | `boolean` | Track acknowledgement of the GPT-5.1 migration prompt. |

118| `notice.hide_world_writable_warning` | `boolean` | Track acknowledgement of the Windows world-writable directories warning. |144| `notice.hide_world_writable_warning` | `boolean` | Track acknowledgement of the Windows world-writable directories warning. |

119| `notice.model_migrations` | `map<string,string>` | Track acknowledged model migrations as old->new mappings. |145| `notice.model_migrations` | `map<string,string>` | Track acknowledged model migrations as old->new mappings. |

120| `notify` | `array<string>` | Command invoked for notifications; receives a JSON payload from Codex. |146| `notify` | `array<string>` | Command invoked for notifications; receives a JSON payload from Codex. |

147| `openai_base_url` | `string` | Base URL override for the built-in `openai` model provider. |

121| `oss_provider` | `lmstudio | ollama` | Default local provider used when running with `--oss` (defaults to prompting if unset). |148| `oss_provider` | `lmstudio | ollama` | Default local provider used when running with `--oss` (defaults to prompting if unset). |

122| `otel.environment` | `string` | Environment tag applied to emitted OpenTelemetry events (default: `dev`). |149| `otel.environment` | `string` | Environment tag applied to emitted OpenTelemetry events (default: `dev`). |

123| `otel.exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry exporter and provide any endpoint metadata. |150| `otel.exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry exporter and provide any endpoint metadata. |

128| `otel.exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL exporter TLS. |155| `otel.exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL exporter TLS. |

129| `otel.exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL exporter TLS. |156| `otel.exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL exporter TLS. |

130| `otel.log_user_prompt` | `boolean` | Opt in to exporting raw user prompts with OpenTelemetry logs. |157| `otel.log_user_prompt` | `boolean` | Opt in to exporting raw user prompts with OpenTelemetry logs. |

158| `otel.metrics_exporter` | `none | statsig | otlp-http | otlp-grpc` | Select the OpenTelemetry metrics exporter (defaults to `statsig`). |

131| `otel.trace_exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry trace exporter and provide any endpoint metadata. |159| `otel.trace_exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry trace exporter and provide any endpoint metadata. |

132| `otel.trace_exporter.<id>.endpoint` | `string` | Trace exporter endpoint for OTEL logs. |160| `otel.trace_exporter.<id>.endpoint` | `string` | Trace exporter endpoint for OTEL logs. |

133| `otel.trace_exporter.<id>.headers` | `map<string,string>` | Static headers included with OTEL trace exporter requests. |161| `otel.trace_exporter.<id>.headers` | `map<string,string>` | Static headers included with OTEL trace exporter requests. |

135| `otel.trace_exporter.<id>.tls.ca-certificate` | `string` | CA certificate path for OTEL trace exporter TLS. |163| `otel.trace_exporter.<id>.tls.ca-certificate` | `string` | CA certificate path for OTEL trace exporter TLS. |

136| `otel.trace_exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL trace exporter TLS. |164| `otel.trace_exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL trace exporter TLS. |

137| `otel.trace_exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL trace exporter TLS. |165| `otel.trace_exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL trace exporter TLS. |

166| `permissions.<name>.filesystem` | `table` | Named filesystem permission profile. Each key is an absolute path or special token such as `:minimal` or `:project_roots`. |

167| `permissions.<name>.filesystem.":project_roots".<subpath-or-glob>` | `"read" | "write" | "none"` | Scoped filesystem access relative to the detected project roots. Use `"."` for the root itself; glob subpaths such as `"**/*.env"` can deny reads with `"none"`. |

168| `permissions.<name>.filesystem.<path-or-glob>` | `"read" | "write" | "none" | table` | Grant direct access for a path, glob pattern, or special token, or scope nested entries under that root. Use `"none"` to deny reads for matching paths. |

169| `permissions.<name>.filesystem.glob_scan_max_depth` | `number` | Maximum depth for expanding deny-read glob patterns on platforms that snapshot matches before sandbox startup. Must be at least `1` when set. |

170| `permissions.<name>.network.allow_local_binding` | `boolean` | Permit local bind/listen operations through the managed proxy. |

171| `permissions.<name>.network.allow_upstream_proxy` | `boolean` | Allow the managed proxy to chain to another upstream proxy. |

172| `permissions.<name>.network.dangerously_allow_all_unix_sockets` | `boolean` | Allow the proxy to use arbitrary Unix sockets instead of the default restricted set. |

173| `permissions.<name>.network.dangerously_allow_non_loopback_proxy` | `boolean` | Permit non-loopback bind addresses for the managed proxy listener. |

174| `permissions.<name>.network.domains` | `map<string, allow | deny>` | Domain rules for the managed proxy. Use domain names or wildcard patterns as keys, with `allow` or `deny` values. |

175| `permissions.<name>.network.enable_socks5` | `boolean` | Expose a SOCKS5 listener when this permissions profile enables the managed network proxy. |

176| `permissions.<name>.network.enable_socks5_udp` | `boolean` | Allow UDP over the SOCKS5 listener when enabled. |

177| `permissions.<name>.network.enabled` | `boolean` | Enable network access for this named permissions profile. |

178| `permissions.<name>.network.mode` | `limited | full` | Network proxy mode used for subprocess traffic. |

179| `permissions.<name>.network.proxy_url` | `string` | HTTP proxy endpoint used when this permissions profile enables the managed network proxy. |

180| `permissions.<name>.network.socks_url` | `string` | SOCKS5 proxy endpoint used by this permissions profile. |

181| `permissions.<name>.network.unix_sockets` | `map<string, allow | none>` | Unix socket rules for the managed proxy. Use socket paths as keys, with `allow` or `none` values. |

138| `personality` | `none | friendly | pragmatic` | Default communication style for models that advertise `supportsPersonality`; can be overridden per thread/turn or via `/personality`. |182| `personality` | `none | friendly | pragmatic` | Default communication style for models that advertise `supportsPersonality`; can be overridden per thread/turn or via `/personality`. |

183| `plan_mode_reasoning_effort` | `none | minimal | low | medium | high | xhigh` | Plan-mode-specific reasoning override. When unset, Plan mode uses its built-in preset default. |

139| `profile` | `string` | Default profile applied at startup (equivalent to `--profile`). |184| `profile` | `string` | Default profile applied at startup (equivalent to `--profile`). |

140| `profiles.<name>.*` | `various` | Profile-scoped overrides for any of the supported configuration keys. |185| `profiles.<name>.*` | `various` | Profile-scoped overrides for any of the supported configuration keys. |

141| `profiles.<name>.experimental_use_freeform_apply_patch` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`. |186| `profiles.<name>.analytics.enabled` | `boolean` | Profile-scoped analytics enablement override. |

142| `profiles.<name>.experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec`. |187| `profiles.<name>.experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec`. |

143| `profiles.<name>.include_apply_patch_tool` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`. |

144| `profiles.<name>.model_catalog_json` | `string (path)` | Profile-scoped model catalog JSON path override (applied on startup only; overrides the top-level `model_catalog_json` for that profile). |188| `profiles.<name>.model_catalog_json` | `string (path)` | Profile-scoped model catalog JSON path override (applied on startup only; overrides the top-level `model_catalog_json` for that profile). |

189| `profiles.<name>.model_instructions_file` | `string (path)` | Profile-scoped replacement for the built-in instruction file. |

145| `profiles.<name>.oss_provider` | `lmstudio | ollama` | Profile-scoped OSS provider for `--oss` sessions. |190| `profiles.<name>.oss_provider` | `lmstudio | ollama` | Profile-scoped OSS provider for `--oss` sessions. |

146| `profiles.<name>.personality` | `none | friendly | pragmatic` | Profile-scoped communication style override for supported models. |191| `profiles.<name>.personality` | `none | friendly | pragmatic` | Profile-scoped communication style override for supported models. |

192| `profiles.<name>.plan_mode_reasoning_effort` | `none | minimal | low | medium | high | xhigh` | Profile-scoped Plan-mode reasoning override. |

193| `profiles.<name>.service_tier` | `flex | fast` | Profile-scoped service tier preference for new turns. |

194| `profiles.<name>.tools_view_image` | `boolean` | Enable or disable the `view_image` tool in that profile. |

147| `profiles.<name>.web_search` | `disabled | cached | live` | Profile-scoped web search mode override (default: `"cached"`). |195| `profiles.<name>.web_search` | `disabled | cached | live` | Profile-scoped web search mode override (default: `"cached"`). |

196| `profiles.<name>.windows.sandbox` | `unelevated | elevated` | Profile-scoped Windows sandbox mode override. |

148| `project_doc_fallback_filenames` | `array<string>` | Additional filenames to try when `AGENTS.md` is missing. |197| `project_doc_fallback_filenames` | `array<string>` | Additional filenames to try when `AGENTS.md` is missing. |

149| `project_doc_max_bytes` | `number` | Maximum bytes read from `AGENTS.md` when building project instructions. |198| `project_doc_max_bytes` | `number` | Maximum bytes read from `AGENTS.md` when building project instructions. |

150| `project_root_markers` | `array<string>` | List of project root marker filenames; used when searching parent directories for the project root. |199| `project_root_markers` | `array<string>` | List of project root marker filenames; used when searching parent directories for the project root. |

151| `projects.<path>.trust_level` | `string` | Mark a project or worktree as trusted or untrusted (`"trusted"` | `"untrusted"`). Untrusted projects skip project-scoped `.codex/` layers. |200| `projects.<path>.trust_level` | `string` | Mark a project or worktree as trusted or untrusted (`"trusted"` | `"untrusted"`). Untrusted projects skip project-scoped `.codex/` layers, including project-local config, hooks, and rules. |

152| `review_model` | `string` | Optional model override used by `/review` (defaults to the current session model). |201| `review_model` | `string` | Optional model override used by `/review` (defaults to the current session model). |

153| `sandbox_mode` | `read-only | workspace-write | danger-full-access` | Sandbox policy for filesystem and network access during command execution. |202| `sandbox_mode` | `read-only | workspace-write | danger-full-access` | Sandbox policy for filesystem and network access during command execution. |

154| `sandbox_workspace_write.exclude_slash_tmp` | `boolean` | Exclude `/tmp` from writable roots in workspace-write mode. |203| `sandbox_workspace_write.exclude_slash_tmp` | `boolean` | Exclude `/tmp` from writable roots in workspace-write mode. |

155| `sandbox_workspace_write.exclude_tmpdir_env_var` | `boolean` | Exclude `$TMPDIR` from writable roots in workspace-write mode. |204| `sandbox_workspace_write.exclude_tmpdir_env_var` | `boolean` | Exclude `$TMPDIR` from writable roots in workspace-write mode. |

156| `sandbox_workspace_write.network_access` | `boolean` | Allow outbound network access inside the workspace-write sandbox. |205| `sandbox_workspace_write.network_access` | `boolean` | Allow outbound network access inside the workspace-write sandbox. |

157| `sandbox_workspace_write.writable_roots` | `array<string>` | Additional writable roots when `sandbox_mode = "workspace-write"`. |206| `sandbox_workspace_write.writable_roots` | `array<string>` | Additional writable roots when `sandbox_mode = "workspace-write"`. |

207| `service_tier` | `flex | fast` | Preferred service tier for new turns. |

158| `shell_environment_policy.exclude` | `array<string>` | Glob patterns for removing environment variables after the defaults. |208| `shell_environment_policy.exclude` | `array<string>` | Glob patterns for removing environment variables after the defaults. |

159| `shell_environment_policy.experimental_use_profile` | `boolean` | Use the user shell profile when spawning subprocesses. |209| `shell_environment_policy.experimental_use_profile` | `boolean` | Use the user shell profile when spawning subprocesses. |

160| `shell_environment_policy.ignore_default_excludes` | `boolean` | Keep variables containing KEY/SECRET/TOKEN before other filters run. |210| `shell_environment_policy.ignore_default_excludes` | `boolean` | Keep variables containing KEY/SECRET/TOKEN before other filters run. |

168| `sqlite_home` | `string (path)` | Directory where Codex stores the SQLite-backed state DB used by agent jobs and other resumable runtime state. |218| `sqlite_home` | `string (path)` | Directory where Codex stores the SQLite-backed state DB used by agent jobs and other resumable runtime state. |

169| `suppress_unstable_features_warning` | `boolean` | Suppress the warning that appears when under-development feature flags are enabled. |219| `suppress_unstable_features_warning` | `boolean` | Suppress the warning that appears when under-development feature flags are enabled. |

170| `tool_output_token_limit` | `number` | Token budget for storing individual tool/function outputs in history. |220| `tool_output_token_limit` | `number` | Token budget for storing individual tool/function outputs in history. |

171| `tools.web_search` | `boolean` | Deprecated legacy toggle for web search; prefer the top-level `web_search` setting. |221| `tool_suggest.discoverables` | `array<table>` | Allow tool suggestions for additional discoverable connectors or plugins. Each entry uses `type = "connector"` or `"plugin"` and an `id`. |

222| `tools.view_image` | `boolean` | Enable the local-image attachment tool `view_image`. |

223| `tools.web_search` | `boolean | { context_size = "low|medium|high", allowed_domains = [string], location = { country, region, city, timezone } }` | Optional web search tool configuration. The legacy boolean form is still accepted, but the object form lets you set search context size, allowed domains, and approximate user location. |

172| `tui` | `table` | TUI-specific options such as enabling inline desktop notifications. |224| `tui` | `table` | TUI-specific options such as enabling inline desktop notifications. |

173| `tui.alternate_screen` | `auto | always | never` | Control alternate screen usage for the TUI (default: auto; auto skips it in Zellij to preserve scrollback). |225| `tui.alternate_screen` | `auto | always | never` | Control alternate screen usage for the TUI (default: auto; auto skips it in Zellij to preserve scrollback). |

174| `tui.animations` | `boolean` | Enable terminal animations (welcome screen, shimmer, spinner) (default: true). |226| `tui.animations` | `boolean` | Enable terminal animations (welcome screen, shimmer, spinner) (default: true). |

175| `tui.notification_method` | `auto | osc9 | bel` | Notification method for unfocused terminal notifications (default: auto). |227| `tui.model_availability_nux.<model>` | `integer` | Internal startup-tooltip state keyed by model slug. |

228| `tui.notification_condition` | `unfocused | always` | Control whether TUI notifications fire only when the terminal is unfocused or regardless of focus. Defaults to `unfocused`. |

229| `tui.notification_method` | `auto | osc9 | bel` | Notification method for terminal notifications (default: auto). |

176| `tui.notifications` | `boolean | array<string>` | Enable TUI notifications; optionally restrict to specific event types. |230| `tui.notifications` | `boolean | array<string>` | Enable TUI notifications; optionally restrict to specific event types. |

177| `tui.show_tooltips` | `boolean` | Show onboarding tooltips in the TUI welcome screen (default: true). |231| `tui.show_tooltips` | `boolean` | Show onboarding tooltips in the TUI welcome screen (default: true). |

178| `tui.status_line` | `array<string> | null` | Ordered list of TUI footer status-line item identifiers. `null` disables the status line. |232| `tui.status_line` | `array<string> | null` | Ordered list of TUI footer status-line item identifiers. `null` disables the status line. |

233| `tui.terminal_title` | `array<string> | null` | Ordered list of terminal window/tab title item identifiers. Defaults to `["spinner", "project"]`; `null` disables title updates. |

234| `tui.theme` | `string` | Syntax-highlighting theme override (kebab-case theme name). |

179| `web_search` | `disabled | cached | live` | Web search mode (default: `"cached"`; cached uses an OpenAI-maintained index and does not fetch live pages; if you use `--yolo` or another full access sandbox setting, it defaults to `"live"`). Use `"live"` to fetch the most recent data from the web, or `"disabled"` to remove the tool. |235| `web_search` | `disabled | cached | live` | Web search mode (default: `"cached"`; cached uses an OpenAI-maintained index and does not fetch live pages; if you use `--yolo` or another full access sandbox setting, it defaults to `"live"`). Use `"live"` to fetch the most recent data from the web, or `"disabled"` to remove the tool. |

180| `windows_wsl_setup_acknowledged` | `boolean` | Track Windows onboarding acknowledgement (Windows only). |236| `windows_wsl_setup_acknowledged` | `boolean` | Track Windows onboarding acknowledgement (Windows only). |

181| `windows.sandbox` | `unelevated | elevated` | Windows-only native sandbox mode when running Codex natively on Windows. |237| `windows.sandbox` | `unelevated | elevated` | Windows-only native sandbox mode when running Codex natively on Windows. |

238| `windows.sandbox_private_desktop` | `boolean` | Run the final sandboxed child process on a private desktop by default on native Windows. Set `false` only for compatibility with the older `Winsta0\\Default` behavior. |

182 239 

183Key240Key

184 241 

206 263 

207Key264Key

208 265 

266`agents.<name>.nickname_candidates`

267 

268Type / Values

269 

270`array<string>`

271 

272Details

273 

274Optional pool of display nicknames for spawned agents in that role.

275 

276Key

277 

209`agents.job_max_runtime_seconds`278`agents.job_max_runtime_seconds`

210 279 

211Type / Values280Type / Values

238 307 

239Details308Details

240 309 

241Maximum number of agent threads that can be open concurrently.310Maximum number of agent threads that can be open concurrently. Defaults to `6` when unset.

242 311 

243Key312Key

244 313 

254 323 

255Key324Key

256 325 

326`analytics.enabled`

327 

328Type / Values

329 

330`boolean`

331 

332Details

333 

334Enable or disable analytics for this machine/profile. When unset, the client default applies.

335 

336Key

337 

257`approval_policy`338`approval_policy`

258 339 

259Type / Values340Type / Values

260 341 

261`untrusted | on-request | never | { reject = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool } }`342`untrusted | on-request | never | { granular = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool, request_permissions = bool, skill_approval = bool } }`

343 

344Details

345 

346Controls when Codex pauses for approval before executing commands. You can also use `approval_policy = { granular = { ... } }` to allow or auto-reject specific prompt categories while keeping other prompts interactive. `on-failure` is deprecated; use `on-request` for interactive runs or `never` for non-interactive runs.

347 

348Key

349 

350`approval_policy.granular.mcp_elicitations`

351 

352Type / Values

353 

354`boolean`

355 

356Details

357 

358When `true`, MCP elicitation prompts are allowed to surface instead of being auto-rejected.

359 

360Key

361 

362`approval_policy.granular.request_permissions`

363 

364Type / Values

365 

366`boolean`

262 367 

263Details368Details

264 369 

265Controls when Codex pauses for approval before executing commands. You can also use `approval_policy = { reject = { ... } }` to auto-reject specific prompt categories while keeping other prompts interactive. `on-failure` is deprecated; use `on-request` for interactive runs or `never` for non-interactive runs.370When `true`, prompts from the `request_permissions` tool are allowed to surface.

266 371 

267Key372Key

268 373 

269`approval_policy.reject.mcp_elicitations`374`approval_policy.granular.rules`

270 375 

271Type / Values376Type / Values

272 377 

274 379 

275Details380Details

276 381 

277When `true`, MCP elicitation prompts are auto-rejected instead of shown to the user.382When `true`, approvals triggered by execpolicy `prompt` rules are allowed to surface.

278 383 

279Key384Key

280 385 

281`approval_policy.reject.rules`386`approval_policy.granular.sandbox_approval`

282 387 

283Type / Values388Type / Values

284 389 

286 391 

287Details392Details

288 393 

289When `true`, approvals triggered by execpolicy `prompt` rules are auto-rejected.394When `true`, sandbox escalation approval prompts are allowed to surface.

290 395 

291Key396Key

292 397 

293`approval_policy.reject.sandbox_approval`398`approval_policy.granular.skill_approval`

294 399 

295Type / Values400Type / Values

296 401 

298 403 

299Details404Details

300 405 

301When `true`, sandbox escalation approval prompts are auto-rejected.406When `true`, skill-script approval prompts are allowed to surface.

407 

408Key

409 

410`approvals_reviewer`

411 

412Type / Values

413 

414`user | auto_review`

415 

416Details

417 

418Who reviews eligible approval prompts under `on-request` or granular approval policies. Defaults to `user`; `auto_review` uses the reviewer subagent. This setting doesn't change sandboxing or review actions already allowed inside the sandbox.

302 419 

303Key420Key

304 421 

422 539 

423Key540Key

424 541 

542`auto_review.policy`

543 

544Type / Values

545 

546`string`

547 

548Details

549 

550Local Markdown policy instructions for automatic review. Managed `guardian_policy_config` takes precedence. Blank values are ignored.

551 

552Key

553 

425`background_terminal_max_timeout`554`background_terminal_max_timeout`

426 555 

427Type / Values556Type / Values

470 599 

471Key600Key

472 601 

473`compact_prompt`602`commit_attribution`

474 603 

475Type / Values604Type / Values

476 605 

478 607 

479Details608Details

480 609 

481Inline override for the history compaction prompt.610Override the commit co-author trailer text. Set an empty string to disable automatic attribution.

482 611 

483Key612Key

484 613 

485`developer_instructions`614`compact_prompt`

486 615 

487Type / Values616Type / Values

488 617 

490 619 

491Details620Details

492 621 

493Additional developer instructions injected into the session (optional).622Inline override for the history compaction prompt.

494 623 

495Key624Key

496 625 

497`disable_paste_burst`626`default_permissions`

498 627 

499Type / Values628Type / Values

500 629 

501`boolean`630`string`

502 631 

503Details632Details

504 633 

505Disable burst-paste detection in the TUI.634Name of the default permissions profile to apply to sandboxed tool calls.

506 635 

507Key636Key

508 637 

509`experimental_compact_prompt_file`638`developer_instructions`

510 639 

511Type / Values640Type / Values

512 641 

513`string (path)`642`string`

514 643 

515Details644Details

516 645 

517Load the compaction prompt override from a file (experimental).646Additional developer instructions injected into the session (optional).

518 647 

519Key648Key

520 649 

521`experimental_use_freeform_apply_patch`650`disable_paste_burst`

522 651 

523Type / Values652Type / Values

524 653 

526 655 

527Details656Details

528 657 

529Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform` or `codex --enable apply_patch_freeform`.658Disable burst-paste detection in the TUI.

530 659 

531Key660Key

532 661 

533`experimental_use_unified_exec_tool`662`experimental_compact_prompt_file`

534 663 

535Type / Values664Type / Values

536 665 

537`boolean`666`string (path)`

538 667 

539Details668Details

540 669 

541Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`.670Load the compaction prompt override from a file (experimental).

542 671 

543Key672Key

544 673 

545`features.apply_patch_freeform`674`experimental_use_unified_exec_tool`

546 675 

547Type / Values676Type / Values

548 677 

550 679 

551Details680Details

552 681 

553Expose the freeform `apply_patch` tool (experimental).682Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`.

554 683 

555Key684Key

556 685 

566 695 

567Key696Key

568 697 

569`features.apps_mcp_gateway`698`features.codex_hooks`

570 

571Type / Values

572 

573`boolean`

574 

575Details

576 

577Route Apps MCP calls through the OpenAI connectors MCP gateway (`https://api.openai.com/v1/connectors/mcp/`) instead of legacy routing (experimental).

578 

579Key

580 

581`features.child_agents_md`

582 699 

583Type / Values700Type / Values

584 701 

586 703 

587Details704Details

588 705 

589Append AGENTS.md scope/precedence guidance even when no AGENTS.md is present (experimental).706Enable lifecycle hooks loaded from `hooks.json` or inline `[hooks]` config.

590 707 

591Key708Key

592 709 

593`features.collaboration_modes`710`features.enable_request_compression`

594 711 

595Type / Values712Type / Values

596 713 

598 715 

599Details716Details

600 717 

601Enable collaboration modes such as plan mode (stable; on by default).718Compress streaming request bodies with zstd when supported (stable; on by default).

602 719 

603Key720Key

604 721 

605`features.multi_agent`722`features.fast_mode`

606 723 

607Type / Values724Type / Values

608 725 

610 727 

611Details728Details

612 729 

613Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait`, `close_agent`, and `spawn_agents_on_csv`) (experimental; off by default).730Enable Fast mode selection and the `service_tier = "fast"` path (stable; on by default).

614 731 

615Key732Key

616 733 

617`features.personality`734`features.memories`

618 735 

619Type / Values736Type / Values

620 737 

622 739 

623Details740Details

624 741 

625Enable personality selection controls (stable; on by default).742Enable [Memories](https://developers.openai.com/codex/memories) (off by default).

626 743 

627Key744Key

628 745 

629`features.powershell_utf8`746`features.multi_agent`

630 747 

631Type / Values748Type / Values

632 749 

634 751 

635Details752Details

636 753 

637Force PowerShell UTF-8 output (defaults to true).754Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait_agent`, and `close_agent`) (stable; on by default).

638 755 

639Key756Key

640 757 

641`features.remote_models`758`features.personality`

642 759 

643Type / Values760Type / Values

644 761 

646 763 

647Details764Details

648 765 

649Refresh remote model list before showing readiness (experimental).766Enable personality selection controls (stable; on by default).

650 767 

651Key768Key

652 769 

653`features.request_rule`770`features.prevent_idle_sleep`

654 771 

655Type / Values772Type / Values

656 773 

658 775 

659Details776Details

660 777 

661Enable Smart approvals (`prefix_rule` suggestions on escalation requests; stable; on by default).778Prevent the machine from sleeping while a turn is actively running (experimental; off by default).

662 779 

663Key780Key

664 781 

665`features.runtime_metrics`782`features.shell_snapshot`

666 783 

667Type / Values784Type / Values

668 785 

670 787 

671Details788Details

672 789 

673Show runtime metrics summary in TUI turn separators (experimental).790Snapshot shell environment to speed up repeated commands (stable; on by default).

674 791 

675Key792Key

676 793 

677`features.search_tool`794`features.shell_tool`

678 795 

679Type / Values796Type / Values

680 797 

682 799 

683Details800Details

684 801 

685Enable `search_tool_bm25` for Apps tool discovery before invoking app MCP tools (experimental).802Enable the default `shell` tool for running commands (stable; on by default).

686 803 

687Key804Key

688 805 

689`features.shell_snapshot`806`features.skill_mcp_dependency_install`

690 807 

691Type / Values808Type / Values

692 809 

694 811 

695Details812Details

696 813 

697Snapshot shell environment to speed up repeated commands (beta).814Allow prompting and installing missing MCP dependencies for skills (stable; on by default).

698 815 

699Key816Key

700 817 

701`features.shell_tool`818`features.undo`

702 819 

703Type / Values820Type / Values

704 821 

706 823 

707Details824Details

708 825 

709Enable the default `shell` tool for running commands (stable; on by default).826Enable undo support (stable; off by default).

710 827 

711Key828Key

712 829 

718 835 

719Details836Details

720 837 

721Use the unified PTY-backed exec tool (beta).838Use the unified PTY-backed exec tool (stable; enabled by default except on Windows).

722 

723Key

724 

725`features.use_linux_sandbox_bwrap`

726 

727Type / Values

728 

729`boolean`

730 

731Details

732 

733Use the bubblewrap-based Linux sandbox pipeline (experimental; off by default).

734 839 

735Key840Key

736 841 

854 959 

855Key960Key

856 961 

857`include_apply_patch_tool`962`hooks`

858 963 

859Type / Values964Type / Values

860 965 

861`boolean`966`table`

862 967 

863Details968Details

864 969 

865Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`.970Lifecycle hooks configured inline in `config.toml`. Uses the same event schema as `hooks.json`; see the Hooks guide for examples and supported events.

866 971 

867Key972Key

868 973 

1038 1143 

1039Type / Values1144Type / Values

1040 1145 

1041`array<string>`1146`array<string | { name = string, source = "local" | "remote" }>`

1147 

1148Details

1149 

1150Additional environment variables to whitelist for an MCP stdio server. String entries default to `source = "local"`; use `source = "remote"` only with executor-backed remote stdio.

1151 

1152Key

1153 

1154`mcp_servers.<id>.experimental_environment`

1155 

1156Type / Values

1157 

1158`local | remote`

1042 1159 

1043Details1160Details

1044 1161 

1045Additional environment variables to whitelist for an MCP stdio server.1162Experimental placement for an MCP server. `remote` starts stdio servers through a remote executor environment; streamable HTTP remote placement is not implemented.

1046 1163 

1047Key1164Key

1048 1165 

1058 1175 

1059Key1176Key

1060 1177 

1178`mcp_servers.<id>.oauth_resource`

1179 

1180Type / Values

1181 

1182`string`

1183 

1184Details

1185 

1186Optional RFC 8707 OAuth resource parameter to include during MCP login.

1187 

1188Key

1189 

1061`mcp_servers.<id>.required`1190`mcp_servers.<id>.required`

1062 1191 

1063Type / Values1192Type / Values

1070 1199 

1071Key1200Key

1072 1201 

1202`mcp_servers.<id>.scopes`

1203 

1204Type / Values

1205 

1206`array<string>`

1207 

1208Details

1209 

1210OAuth scopes to request when authenticating to that MCP server.

1211 

1212Key

1213 

1073`mcp_servers.<id>.startup_timeout_ms`1214`mcp_servers.<id>.startup_timeout_ms`

1074 1215 

1075Type / Values1216Type / Values

1118 1259 

1119Key1260Key

1120 1261 

1121`model`1262`memories.consolidation_model`

1122 1263 

1123Type / Values1264Type / Values

1124 1265 

1126 1267 

1127Details1268Details

1128 1269 

1129Model to use (e.g., `gpt-5-codex`).1270Optional model override for global memory consolidation.

1130 1271 

1131Key1272Key

1132 1273 

1133`model_auto_compact_token_limit`1274`memories.disable_on_external_context`

1134 1275 

1135Type / Values1276Type / Values

1136 1277 

1137`number`1278`boolean`

1138 1279 

1139Details1280Details

1140 1281 

1141Token threshold that triggers automatic history compaction (unset uses model defaults).1282When `true`, threads that use external context such as MCP tool calls, web search, or tool search are kept out of memory generation. Defaults to `false`. Legacy alias: `memories.no_memories_if_mcp_or_web_search`.

1142 1283 

1143Key1284Key

1144 1285 

1145`model_catalog_json`1286`memories.extract_model`

1146 1287 

1147Type / Values1288Type / Values

1148 1289 

1149`string (path)`1290`string`

1150 1291 

1151Details1292Details

1152 1293 

1153Optional path to a JSON model catalog loaded on startup. Profile-level `profiles.<name>.model_catalog_json` can override this per profile.1294Optional model override for per-thread memory extraction.

1154 1295 

1155Key1296Key

1156 1297 

1157`model_context_window`1298`memories.generate_memories`

1158 1299 

1159Type / Values1300Type / Values

1160 1301 

1161`number`1302`boolean`

1162 1303 

1163Details1304Details

1164 1305 

1165Context window tokens available to the active model.1306When `false`, newly created threads are not stored as memory-generation inputs. Defaults to `true`.

1166 1307 

1167Key1308Key

1168 1309 

1169`model_instructions_file`1310`memories.max_raw_memories_for_consolidation`

1170 1311 

1171Type / Values1312Type / Values

1172 1313 

1173`string (path)`1314`number`

1174 1315 

1175Details1316Details

1176 1317 

1177Replacement for built-in instructions instead of `AGENTS.md`.1318Maximum recent raw memories retained for global consolidation. Defaults to `256` and is capped at `4096`.

1178 1319 

1179Key1320Key

1180 1321 

1181`model_provider`1322`memories.max_rollout_age_days`

1182 1323 

1183Type / Values1324Type / Values

1184 1325 

1185`string`1326`number`

1186 1327 

1187Details1328Details

1188 1329 

1189Provider id from `model_providers` (default: `openai`).1330Maximum age of threads considered for memory generation. Defaults to `30` and is clamped to `0`-`90`.

1190 1331 

1191Key1332Key

1192 1333 

1193`model_providers.<id>.base_url`1334`memories.max_rollouts_per_startup`

1194 1335 

1195Type / Values1336Type / Values

1196 1337 

1197`string`1338`number`

1198 1339 

1199Details1340Details

1200 1341 

1201API base URL for the model provider.1342Maximum rollout candidates processed per startup pass. Defaults to `16` and is capped at `128`.

1202 1343 

1203Key1344Key

1204 1345 

1205`model_providers.<id>.env_http_headers`1346`memories.max_unused_days`

1206 1347 

1207Type / Values1348Type / Values

1208 1349 

1209`map<string,string>`1350`number`

1210 1351 

1211Details1352Details

1212 1353 

1213HTTP headers populated from environment variables when present.1354Maximum days since a memory was last used before it becomes ineligible for consolidation. Defaults to `30` and is clamped to `0`-`365`.

1214 1355 

1215Key1356Key

1216 1357 

1217`model_providers.<id>.env_key`1358`memories.min_rate_limit_remaining_percent`

1218 1359 

1219Type / Values1360Type / Values

1220 1361 

1221`string`1362`number`

1222 1363 

1223Details1364Details

1224 1365 

1225Environment variable supplying the provider API key.1366Minimum remaining percentage required in Codex rate-limit windows before memory generation starts. Defaults to `25` and is clamped to `0`-`100`.

1226 1367 

1227Key1368Key

1228 1369 

1229`model_providers.<id>.env_key_instructions`1370`memories.min_rollout_idle_hours`

1230 1371 

1231Type / Values1372Type / Values

1232 1373 

1233`string`1374`number`

1234 1375 

1235Details1376Details

1236 1377 

1237Optional setup guidance for the provider API key.1378Minimum idle time before a thread is considered for memory generation. Defaults to `6` and is clamped to `1`-`48`.

1238 1379 

1239Key1380Key

1240 1381 

1241`model_providers.<id>.experimental_bearer_token`1382`memories.use_memories`

1242 1383 

1243Type / Values1384Type / Values

1244 1385 

1245`string`1386`boolean`

1246 1387 

1247Details1388Details

1248 1389 

1249Direct bearer token for the provider (discouraged; use `env_key`).1390When `false`, Codex skips injecting existing memories into future sessions. Defaults to `true`.

1250 1391 

1251Key1392Key

1252 1393 

1253`model_providers.<id>.http_headers`1394`model`

1254 1395 

1255Type / Values1396Type / Values

1256 1397 

1257`map<string,string>`1398`string`

1258 1399 

1259Details1400Details

1260 1401 

1261Static HTTP headers added to provider requests.1402Model to use (e.g., `gpt-5.5`).

1262 1403 

1263Key1404Key

1264 1405 

1265`model_providers.<id>.name`1406`model_auto_compact_token_limit`

1266 1407 

1267Type / Values1408Type / Values

1268 1409 

1269`string`1410`number`

1270 1411 

1271Details1412Details

1272 1413 

1273Display name for a custom model provider.1414Token threshold that triggers automatic history compaction (unset uses model defaults).

1274 1415 

1275Key1416Key

1276 1417 

1277`model_providers.<id>.query_params`1418`model_catalog_json`

1278 1419 

1279Type / Values1420Type / Values

1280 1421 

1281`map<string,string>`1422`string (path)`

1282 1423 

1283Details1424Details

1284 1425 

1285Extra query parameters appended to provider requests.1426Optional path to a JSON model catalog loaded on startup. Profile-level `profiles.<name>.model_catalog_json` can override this per profile.

1286 1427 

1287Key1428Key

1288 1429 

1289`model_providers.<id>.request_max_retries`1430`model_context_window`

1290 1431 

1291Type / Values1432Type / Values

1292 1433 

1294 1435 

1295Details1436Details

1296 1437 

1297Retry count for HTTP requests to the provider (default: 4).1438Context window tokens available to the active model.

1298 1439 

1299Key1440Key

1300 1441 

1301`model_providers.<id>.requires_openai_auth`1442`model_instructions_file`

1302 1443 

1303Type / Values1444Type / Values

1304 1445 

1305`boolean`1446`string (path)`

1306 1447 

1307Details1448Details

1308 1449 

1309The provider uses OpenAI authentication (defaults to false).1450Replacement for built-in instructions instead of `AGENTS.md`.

1310 1451 

1311Key1452Key

1312 1453 

1313`model_providers.<id>.stream_idle_timeout_ms`1454`model_provider`

1314 1455 

1315Type / Values1456Type / Values

1316 1457 

1317`number`1458`string`

1318 1459 

1319Details1460Details

1320 1461 

1321Idle timeout for SSE streams in milliseconds (default: 300000).1462Provider id from `model_providers` (default: `openai`).

1322 1463 

1323Key1464Key

1324 1465 

1325`model_providers.<id>.stream_max_retries`1466`model_providers.<id>`

1326 1467 

1327Type / Values1468Type / Values

1328 1469 

1329`number`1470`table`

1330 1471 

1331Details1472Details

1332 1473 

1333Retry count for SSE streaming interruptions (default: 5).1474Custom provider definition. Built-in provider IDs (`openai`, `ollama`, and `lmstudio`) are reserved and cannot be overridden.

1334 1475 

1335Key1476Key

1336 1477 

1337`model_providers.<id>.wire_api`1478`model_providers.<id>.auth`

1338 1479 

1339Type / Values1480Type / Values

1340 1481 

1341`chat | responses`1482`table`

1342 1483 

1343Details1484Details

1344 1485 

1345Protocol used by the provider (defaults to `chat` if omitted).1486Command-backed bearer token configuration for a custom provider. Do not combine with `env_key`, `experimental_bearer_token`, or `requires_openai_auth`.

1346 1487 

1347Key1488Key

1348 1489 

1349`model_reasoning_effort`1490`model_providers.<id>.auth.args`

1350 1491 

1351Type / Values1492Type / Values

1352 1493 

1353`minimal | low | medium | high | xhigh`1494`array<string>`

1354 1495 

1355Details1496Details

1356 1497 

1357Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent).1498Arguments passed to the token command.

1358 1499 

1359Key1500Key

1360 1501 

1361`model_reasoning_summary`1502`model_providers.<id>.auth.command`

1362 1503 

1363Type / Values1504Type / Values

1364 1505 

1365`auto | concise | detailed | none`1506`string`

1366 1507 

1367Details1508Details

1368 1509 

1369Select reasoning summary detail or disable summaries entirely.1510Command to run when Codex needs a bearer token. The command must print the token to stdout.

1370 1511 

1371Key1512Key

1372 1513 

1373`model_supports_reasoning_summaries`1514`model_providers.<id>.auth.cwd`

1374 1515 

1375Type / Values1516Type / Values

1376 1517 

1377`boolean`1518`string (path)`

1378 1519 

1379Details1520Details

1380 1521 

1381Force Codex to send or not send reasoning metadata.1522Working directory for the token command.

1382 1523 

1383Key1524Key

1384 1525 

1385`model_verbosity`1526`model_providers.<id>.auth.refresh_interval_ms`

1386 1527 

1387Type / Values1528Type / Values

1388 1529 

1389`low | medium | high`1530`number`

1390 1531 

1391Details1532Details

1392 1533 

1393Control GPT-5 Responses API verbosity (defaults to `medium`).1534How often Codex proactively refreshes the token in milliseconds (default: 300000). Set to `0` to refresh only after an authentication retry.

1394 1535 

1395Key1536Key

1396 1537 

1397`notice.hide_full_access_warning`1538`model_providers.<id>.auth.timeout_ms`

1398 1539 

1399Type / Values1540Type / Values

1400 1541 

1401`boolean`1542`number`

1402 1543 

1403Details1544Details

1404 1545 

1405Track acknowledgement of the full access warning prompt.1546Maximum token command runtime in milliseconds (default: 5000).

1406 1547 

1407Key1548Key

1408 1549 

1409`notice.hide_gpt-5.1-codex-max_migration_prompt`1550`model_providers.<id>.base_url`

1410 1551 

1411Type / Values1552Type / Values

1412 1553 

1413`boolean`1554`string`

1414 1555 

1415Details1556Details

1416 1557 

1417Track acknowledgement of the gpt-5.1-codex-max migration prompt.1558API base URL for the model provider.

1418 1559 

1419Key1560Key

1420 1561 

1421`notice.hide_gpt5_1_migration_prompt`1562`model_providers.<id>.env_http_headers`

1563 

1564Type / Values

1565 

1566`map<string,string>`

1567 

1568Details

1569 

1570HTTP headers populated from environment variables when present.

1571 

1572Key

1573 

1574`model_providers.<id>.env_key`

1575 

1576Type / Values

1577 

1578`string`

1579 

1580Details

1581 

1582Environment variable supplying the provider API key.

1583 

1584Key

1585 

1586`model_providers.<id>.env_key_instructions`

1587 

1588Type / Values

1589 

1590`string`

1591 

1592Details

1593 

1594Optional setup guidance for the provider API key.

1595 

1596Key

1597 

1598`model_providers.<id>.experimental_bearer_token`

1599 

1600Type / Values

1601 

1602`string`

1603 

1604Details

1605 

1606Direct bearer token for the provider (discouraged; use `env_key`).

1607 

1608Key

1609 

1610`model_providers.<id>.http_headers`

1611 

1612Type / Values

1613 

1614`map<string,string>`

1615 

1616Details

1617 

1618Static HTTP headers added to provider requests.

1619 

1620Key

1621 

1622`model_providers.<id>.name`

1623 

1624Type / Values

1625 

1626`string`

1627 

1628Details

1629 

1630Display name for a custom model provider.

1631 

1632Key

1633 

1634`model_providers.<id>.query_params`

1635 

1636Type / Values

1637 

1638`map<string,string>`

1639 

1640Details

1641 

1642Extra query parameters appended to provider requests.

1643 

1644Key

1645 

1646`model_providers.<id>.request_max_retries`

1647 

1648Type / Values

1649 

1650`number`

1651 

1652Details

1653 

1654Retry count for HTTP requests to the provider (default: 4).

1655 

1656Key

1657 

1658`model_providers.<id>.requires_openai_auth`

1659 

1660Type / Values

1661 

1662`boolean`

1663 

1664Details

1665 

1666The provider uses OpenAI authentication (defaults to false).

1667 

1668Key

1669 

1670`model_providers.<id>.stream_idle_timeout_ms`

1671 

1672Type / Values

1673 

1674`number`

1675 

1676Details

1677 

1678Idle timeout for SSE streams in milliseconds (default: 300000).

1679 

1680Key

1681 

1682`model_providers.<id>.stream_max_retries`

1683 

1684Type / Values

1685 

1686`number`

1687 

1688Details

1689 

1690Retry count for SSE streaming interruptions (default: 5).

1691 

1692Key

1693 

1694`model_providers.<id>.supports_websockets`

1695 

1696Type / Values

1697 

1698`boolean`

1699 

1700Details

1701 

1702Whether that provider supports the Responses API WebSocket transport.

1703 

1704Key

1705