config-reference.md Codex Docs, 2026-03-03 00:35 UTC → 2026-04-29 00:50 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. |

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. |

15| `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). |

16| `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. |

17| `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. |

18| `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. |

19| `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. |

20| `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. |

21| `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. |

22| `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`. |

23| `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. |

24| `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`. |

29| `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`. |

30| `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. |

31| `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. |

32| `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. |

33| `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. |

34| `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). |

35| `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. |

36| `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. |

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

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

39| `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). |

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

41| `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`. |

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

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

44| `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. |

45| `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). |

46| `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). |

47| `features.multi_agent` | `boolean` | Enable multi-agent collaboration tools (`spawn\_agent`, `send\_input`, `resume\_agent`, `wait`, and `close\_agent`) (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). |

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

49| `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). |

50| `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). |

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

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

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

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

55| `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). |

56| `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). |

57| `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). |

58| `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. |

59| `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"`. |

60| `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"`. |

65| `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. |

66| `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. |

67| `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. |

68| `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. |

69| `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`. |

70| `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`. |

71| `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. |

80| `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. |

81| `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. |

82| `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. |

83| `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. |

84| `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. |

85| `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. |

86| `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. |

87| `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. |

88| `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. |

89| `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. |

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

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

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

91| `model_auto_compact_token_limit` | `number` | Token threshold that triggers automatic history compaction (unset uses model defaults). |109| `model_auto_compact_token_limit` | `number` | Token threshold that triggers automatic history compaction (unset uses model defaults). |

92| `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. |110| `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. |

93| `model_context_window` | `number` | Context window tokens available to the active model. |111| `model_context_window` | `number` | Context window tokens available to the active model. |

94| `model_instructions_file` | `string (path)` | Replacement for built-in instructions instead of `AGENTS.md`. |112| `model_instructions_file` | `string (path)` | Replacement for built-in instructions instead of `AGENTS.md`. |

95| `model_provider` | `string` | Provider id from `model_providers` (default: `openai`). |113| `model_provider` | `string` | Provider id from `model_providers` (default: `openai`). |

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

115| `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`. |

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

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

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

119| `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. |

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

96| `model_providers.<id>.base_url` | `string` | API base URL for the model provider. |121| `model_providers.<id>.base_url` | `string` | API base URL for the model provider. |

97| `model_providers.<id>.env_http_headers` | `map<string,string>` | HTTP headers populated from environment variables when present. |122| `model_providers.<id>.env_http_headers` | `map<string,string>` | HTTP headers populated from environment variables when present. |

98| `model_providers.<id>.env_key` | `string` | Environment variable supplying the provider API key. |123| `model_providers.<id>.env_key` | `string` | Environment variable supplying the provider API key. |

105| `model_providers.<id>.requires_openai_auth` | `boolean` | The provider uses OpenAI authentication (defaults to false). |130| `model_providers.<id>.requires_openai_auth` | `boolean` | The provider uses OpenAI authentication (defaults to false). |

106| `model_providers.<id>.stream_idle_timeout_ms` | `number` | Idle timeout for SSE streams in milliseconds (default: 300000). |131| `model_providers.<id>.stream_idle_timeout_ms` | `number` | Idle timeout for SSE streams in milliseconds (default: 300000). |

107| `model_providers.<id>.stream_max_retries` | `number` | Retry count for SSE streaming interruptions (default: 5). |132| `model_providers.<id>.stream_max_retries` | `number` | Retry count for SSE streaming interruptions (default: 5). |

108| `model_providers.<id>.wire_api` | `chat | responses` | Protocol used by the provider (defaults to `chat` if omitted). |133| `model_providers.<id>.supports_websockets` | `boolean` | Whether that provider supports the Responses API WebSocket transport. |

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

109| `model_reasoning_effort` | `minimal | low | medium | high | xhigh` | Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent). |135| `model_reasoning_effort` | `minimal | low | medium | high | xhigh` | Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent). |

110| `model_reasoning_summary` | `auto | concise | detailed | none` | Select reasoning summary detail or disable summaries entirely. |136| `model_reasoning_summary` | `auto | concise | detailed | none` | Select reasoning summary detail or disable summaries entirely. |

111| `model_supports_reasoning_summaries` | `boolean` | Force Codex to send or not send reasoning metadata. |137| `model_supports_reasoning_summaries` | `boolean` | Force Codex to send or not send reasoning metadata. |

112| `model_verbosity` | `low | medium | high` | Control GPT-5 Responses API verbosity (defaults to `medium`). |138| `model_verbosity` | `low | medium | high` | Optional GPT-5 Responses API verbosity override; when unset, the selected model/preset default is used. |

113| `notice.hide_full_access_warning` | `boolean` | Track acknowledgement of the full access warning prompt. |139| `notice.hide_full_access_warning` | `boolean` | Track acknowledgement of the full access warning prompt. |

114| `notice.hide_gpt-5.1-codex-max_migration_prompt` | `boolean` | Track acknowledgement of the gpt-5.1-codex-max migration prompt. |140| `notice.hide_gpt-5.1-codex-max_migration_prompt` | `boolean` | Track acknowledgement of the gpt-5.1-codex-max migration prompt. |

115| `notice.hide_gpt5_1_migration_prompt` | `boolean` | Track acknowledgement of the GPT-5.1 migration prompt. |141| `notice.hide_gpt5_1_migration_prompt` | `boolean` | Track acknowledgement of the GPT-5.1 migration prompt. |

117| `notice.hide_world_writable_warning` | `boolean` | Track acknowledgement of the Windows world-writable directories warning. |143| `notice.hide_world_writable_warning` | `boolean` | Track acknowledgement of the Windows world-writable directories warning. |

118| `notice.model_migrations` | `map<string,string>` | Track acknowledged model migrations as old->new mappings. |144| `notice.model_migrations` | `map<string,string>` | Track acknowledged model migrations as old->new mappings. |

119| `notify` | `array<string>` | Command invoked for notifications; receives a JSON payload from Codex. |145| `notify` | `array<string>` | Command invoked for notifications; receives a JSON payload from Codex. |

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

120| `oss_provider` | `lmstudio | ollama` | Default local provider used when running with `--oss` (defaults to prompting if unset). |147| `oss_provider` | `lmstudio | ollama` | Default local provider used when running with `--oss` (defaults to prompting if unset). |

121| `otel.environment` | `string` | Environment tag applied to emitted OpenTelemetry events (default: `dev`). |148| `otel.environment` | `string` | Environment tag applied to emitted OpenTelemetry events (default: `dev`). |

122| `otel.exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry exporter and provide any endpoint metadata. |149| `otel.exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry exporter and provide any endpoint metadata. |

127| `otel.exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL exporter TLS. |154| `otel.exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL exporter TLS. |

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

129| `otel.log_user_prompt` | `boolean` | Opt in to exporting raw user prompts with OpenTelemetry logs. |156| `otel.log_user_prompt` | `boolean` | Opt in to exporting raw user prompts with OpenTelemetry logs. |

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

130| `otel.trace_exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry trace exporter and provide any endpoint metadata. |158| `otel.trace_exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry trace exporter and provide any endpoint metadata. |

131| `otel.trace_exporter.<id>.endpoint` | `string` | Trace exporter endpoint for OTEL logs. |159| `otel.trace_exporter.<id>.endpoint` | `string` | Trace exporter endpoint for OTEL logs. |

132| `otel.trace_exporter.<id>.headers` | `map<string,string>` | Static headers included with OTEL trace exporter requests. |160| `otel.trace_exporter.<id>.headers` | `map<string,string>` | Static headers included with OTEL trace exporter requests. |

134| `otel.trace_exporter.<id>.tls.ca-certificate` | `string` | CA certificate path for OTEL trace exporter TLS. |162| `otel.trace_exporter.<id>.tls.ca-certificate` | `string` | CA certificate path for OTEL trace exporter TLS. |

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

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

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

166| `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"`. |

167| `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. |

168| `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. |

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

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

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

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

173| `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. |

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

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

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

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

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

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

180| `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. |

137| `personality` | `none | friendly | pragmatic` | Default communication style for models that advertise `supportsPersonality`; can be overridden per thread/turn or via `/personality`. |181| `personality` | `none | friendly | pragmatic` | Default communication style for models that advertise `supportsPersonality`; can be overridden per thread/turn or via `/personality`. |

182| `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. |

138| `profile` | `string` | Default profile applied at startup (equivalent to `--profile`). |183| `profile` | `string` | Default profile applied at startup (equivalent to `--profile`). |

139| `profiles.<name>.*` | `various` | Profile-scoped overrides for any of the supported configuration keys. |184| `profiles.<name>.*` | `various` | Profile-scoped overrides for any of the supported configuration keys. |

140| `profiles.<name>.experimental_use_freeform_apply_patch` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`. |185| `profiles.<name>.analytics.enabled` | `boolean` | Profile-scoped analytics enablement override. |

141| `profiles.<name>.experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec`. |186| `profiles.<name>.experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec`. |

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

143| `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). |187| `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_instructions_file` | `string (path)` | Profile-scoped replacement for the built-in instruction file. |

144| `profiles.<name>.oss_provider` | `lmstudio | ollama` | Profile-scoped OSS provider for `--oss` sessions. |189| `profiles.<name>.oss_provider` | `lmstudio | ollama` | Profile-scoped OSS provider for `--oss` sessions. |

145| `profiles.<name>.personality` | `none | friendly | pragmatic` | Profile-scoped communication style override for supported models. |190| `profiles.<name>.personality` | `none | friendly | pragmatic` | Profile-scoped communication style override for supported models. |

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

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

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

146| `profiles.<name>.web_search` | `disabled | cached | live` | Profile-scoped web search mode override (default: `"cached"`). |194| `profiles.<name>.web_search` | `disabled | cached | live` | Profile-scoped web search mode override (default: `"cached"`). |

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

147| `project_doc_fallback_filenames` | `array<string>` | Additional filenames to try when `AGENTS.md` is missing. |196| `project_doc_fallback_filenames` | `array<string>` | Additional filenames to try when `AGENTS.md` is missing. |

148| `project_doc_max_bytes` | `number` | Maximum bytes read from `AGENTS.md` when building project instructions. |197| `project_doc_max_bytes` | `number` | Maximum bytes read from `AGENTS.md` when building project instructions. |

149| `project_root_markers` | `array<string>` | List of project root marker filenames; used when searching parent directories for the project root. |198| `project_root_markers` | `array<string>` | List of project root marker filenames; used when searching parent directories for the project root. |

150| `projects.<path>.trust_level` | `string` | Mark a project or worktree as trusted or untrusted (`"trusted"` | `"untrusted"`). Untrusted projects skip project-scoped `.codex/` layers. |199| `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. |

151| `review_model` | `string` | Optional model override used by `/review` (defaults to the current session model). |200| `review_model` | `string` | Optional model override used by `/review` (defaults to the current session model). |

152| `sandbox_mode` | `read-only | workspace-write | danger-full-access` | Sandbox policy for filesystem and network access during command execution. |201| `sandbox_mode` | `read-only | workspace-write | danger-full-access` | Sandbox policy for filesystem and network access during command execution. |

153| `sandbox_workspace_write.exclude_slash_tmp` | `boolean` | Exclude `/tmp` from writable roots in workspace-write mode. |202| `sandbox_workspace_write.exclude_slash_tmp` | `boolean` | Exclude `/tmp` from writable roots in workspace-write mode. |

154| `sandbox_workspace_write.exclude_tmpdir_env_var` | `boolean` | Exclude `$TMPDIR` from writable roots in workspace-write mode. |203| `sandbox_workspace_write.exclude_tmpdir_env_var` | `boolean` | Exclude `$TMPDIR` from writable roots in workspace-write mode. |

155| `sandbox_workspace_write.network_access` | `boolean` | Allow outbound network access inside the workspace-write sandbox. |204| `sandbox_workspace_write.network_access` | `boolean` | Allow outbound network access inside the workspace-write sandbox. |

156| `sandbox_workspace_write.writable_roots` | `array<string>` | Additional writable roots when `sandbox_mode = "workspace-write"`. |205| `sandbox_workspace_write.writable_roots` | `array<string>` | Additional writable roots when `sandbox_mode = "workspace-write"`. |

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

157| `shell_environment_policy.exclude` | `array<string>` | Glob patterns for removing environment variables after the defaults. |207| `shell_environment_policy.exclude` | `array<string>` | Glob patterns for removing environment variables after the defaults. |

158| `shell_environment_policy.experimental_use_profile` | `boolean` | Use the user shell profile when spawning subprocesses. |208| `shell_environment_policy.experimental_use_profile` | `boolean` | Use the user shell profile when spawning subprocesses. |

159| `shell_environment_policy.ignore_default_excludes` | `boolean` | Keep variables containing KEY/SECRET/TOKEN before other filters run. |209| `shell_environment_policy.ignore_default_excludes` | `boolean` | Keep variables containing KEY/SECRET/TOKEN before other filters run. |

164| `skills.config` | `array<object>` | Per-skill enablement overrides stored in config.toml. |214| `skills.config` | `array<object>` | Per-skill enablement overrides stored in config.toml. |

165| `skills.config.<index>.enabled` | `boolean` | Enable or disable the referenced skill. |215| `skills.config.<index>.enabled` | `boolean` | Enable or disable the referenced skill. |

166| `skills.config.<index>.path` | `string (path)` | Path to a skill folder containing `SKILL.md`. |216| `skills.config.<index>.path` | `string (path)` | Path to a skill folder containing `SKILL.md`. |

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

167| `suppress_unstable_features_warning` | `boolean` | Suppress the warning that appears when under-development feature flags are enabled. |218| `suppress_unstable_features_warning` | `boolean` | Suppress the warning that appears when under-development feature flags are enabled. |

168| `tool_output_token_limit` | `number` | Token budget for storing individual tool/function outputs in history. |219| `tool_output_token_limit` | `number` | Token budget for storing individual tool/function outputs in history. |

169| `tools.web_search` | `boolean` | Deprecated legacy toggle for web search; prefer the top-level `web_search` setting. |220| `tool_suggest.discoverables` | `array<table>` | Allow tool suggestions for additional discoverable connectors or plugins. Each entry uses `type = "connector"` or `"plugin"` and an `id`. |

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

222| `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. |

170| `tui` | `table` | TUI-specific options such as enabling inline desktop notifications. |223| `tui` | `table` | TUI-specific options such as enabling inline desktop notifications. |

171| `tui.alternate_screen` | `auto | always | never` | Control alternate screen usage for the TUI (default: auto; auto skips it in Zellij to preserve scrollback). |224| `tui.alternate_screen` | `auto | always | never` | Control alternate screen usage for the TUI (default: auto; auto skips it in Zellij to preserve scrollback). |

172| `tui.animations` | `boolean` | Enable terminal animations (welcome screen, shimmer, spinner) (default: true). |225| `tui.animations` | `boolean` | Enable terminal animations (welcome screen, shimmer, spinner) (default: true). |

173| `tui.notification_method` | `auto | osc9 | bel` | Notification method for unfocused terminal notifications (default: auto). |226| `tui.model_availability_nux.<model>` | `integer` | Internal startup-tooltip state keyed by model slug. |

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

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

174| `tui.notifications` | `boolean | array<string>` | Enable TUI notifications; optionally restrict to specific event types. |229| `tui.notifications` | `boolean | array<string>` | Enable TUI notifications; optionally restrict to specific event types. |

175| `tui.show_tooltips` | `boolean` | Show onboarding tooltips in the TUI welcome screen (default: true). |230| `tui.show_tooltips` | `boolean` | Show onboarding tooltips in the TUI welcome screen (default: true). |

176| `tui.status_line` | `array<string> | null` | Ordered list of TUI footer status-line item identifiers. `null` disables the status line. |231| `tui.status_line` | `array<string> | null` | Ordered list of TUI footer status-line item identifiers. `null` disables the status line. |

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

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

177| `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. |234| `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. |

178| `windows_wsl_setup_acknowledged` | `boolean` | Track Windows onboarding acknowledgement (Windows only). |235| `windows_wsl_setup_acknowledged` | `boolean` | Track Windows onboarding acknowledgement (Windows only). |

179| `windows.sandbox` | `unelevated | elevated` | Windows-only native sandbox mode when running Codex natively on Windows. |236| `windows.sandbox` | `unelevated | elevated` | Windows-only native sandbox mode when running Codex natively on Windows. |

237| `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. |

180 238 

181Key239Key

182 240 

204 262 

205Key263Key

206 264 

265`agents.<name>.nickname_candidates`

266 

267Type / Values

268 

269`array<string>`

270 

271Details

272 

273Optional pool of display nicknames for spawned agents in that role.

274 

275Key

276 

277`agents.job_max_runtime_seconds`

278 

279Type / Values

280 

281`number`

282 

283Details

284 

285Default per-worker timeout for `spawn_agents_on_csv` jobs. When unset, the tool falls back to 1800 seconds per worker.

286 

287Key

288 

207`agents.max_depth`289`agents.max_depth`

208 290 

209Type / Values291Type / Values

224 306 

225Details307Details

226 308 

227Maximum number of agent threads that can be open concurrently.309Maximum number of agent threads that can be open concurrently. Defaults to `6` when unset.

228 310 

229Key311Key

230 312 

240 322 

241Key323Key

242 324 

325`analytics.enabled`

326 

327Type / Values

328 

329`boolean`

330 

331Details

332 

333Enable or disable analytics for this machine/profile. When unset, the client default applies.

334 

335Key

336 

243`approval_policy`337`approval_policy`

244 338 

245Type / Values339Type / Values

246 340 

247`untrusted | on-request | never | { reject = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool } }`341`untrusted | on-request | never | { granular = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool, request_permissions = bool, skill_approval = bool } }`

342 

343Details

344 

345Controls 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.

346 

347Key

348 

349`approval_policy.granular.mcp_elicitations`

350 

351Type / Values

352 

353`boolean`

354 

355Details

356 

357When `true`, MCP elicitation prompts are allowed to surface instead of being auto-rejected.

358 

359Key

360 

361`approval_policy.granular.request_permissions`

362 

363Type / Values

364 

365`boolean`

248 366 

249Details367Details

250 368 

251Controls 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.369When `true`, prompts from the `request_permissions` tool are allowed to surface.

252 370 

253Key371Key

254 372 

255`approval_policy.reject.mcp_elicitations`373`approval_policy.granular.rules`

256 374 

257Type / Values375Type / Values

258 376 

260 378 

261Details379Details

262 380 

263When `true`, MCP elicitation prompts are auto-rejected instead of shown to the user.381When `true`, approvals triggered by execpolicy `prompt` rules are allowed to surface.

264 382 

265Key383Key

266 384 

267`approval_policy.reject.rules`385`approval_policy.granular.sandbox_approval`

268 386 

269Type / Values387Type / Values

270 388 

272 390 

273Details391Details

274 392 

275When `true`, approvals triggered by execpolicy `prompt` rules are auto-rejected.393When `true`, sandbox escalation approval prompts are allowed to surface.

276 394 

277Key395Key

278 396 

279`approval_policy.reject.sandbox_approval`397`approval_policy.granular.skill_approval`

280 398 

281Type / Values399Type / Values

282 400 

284 402 

285Details403Details

286 404 

287When `true`, sandbox escalation approval prompts are auto-rejected.405When `true`, skill-script approval prompts are allowed to surface.

406 

407Key

408 

409`approvals_reviewer`

410 

411Type / Values

412 

413`user | auto_review`

414 

415Details

416 

417Who 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.

288 418 

289Key419Key

290 420 

408 538 

409Key539Key

410 540 

541`auto_review.policy`

542 

543Type / Values

544 

545`string`

546 

547Details

548 

549Local Markdown policy instructions for automatic review. Managed `guardian_policy_config` takes precedence. Blank values are ignored.

550 

551Key

552 

411`background_terminal_max_timeout`553`background_terminal_max_timeout`

412 554 

413Type / Values555Type / Values

456 598 

457Key599Key

458 600 

459`compact_prompt`601`commit_attribution`

460 602 

461Type / Values603Type / Values

462 604 

464 606 

465Details607Details

466 608 

467Inline override for the history compaction prompt.609Override the commit co-author trailer text. Set an empty string to disable automatic attribution.

468 610 

469Key611Key

470 612 

471`developer_instructions`613`compact_prompt`

472 614 

473Type / Values615Type / Values

474 616 

476 618 

477Details619Details

478 620 

479Additional developer instructions injected into the session (optional).621Inline override for the history compaction prompt.

480 622 

481Key623Key

482 624 

483`disable_paste_burst`625`default_permissions`

484 626 

485Type / Values627Type / Values

486 628 

487`boolean`629`string`

488 630 

489Details631Details

490 632 

491Disable burst-paste detection in the TUI.633Name of the default permissions profile to apply to sandboxed tool calls.

492 634 

493Key635Key

494 636 

495`experimental_compact_prompt_file`637`developer_instructions`

496 638 

497Type / Values639Type / Values

498 640 

499`string (path)`641`string`

500 642 

501Details643Details

502 644 

503Load the compaction prompt override from a file (experimental).645Additional developer instructions injected into the session (optional).

504 646 

505Key647Key

506 648 

507`experimental_use_freeform_apply_patch`649`disable_paste_burst`

508 650 

509Type / Values651Type / Values

510 652 

512 654 

513Details655Details

514 656 

515Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform` or `codex --enable apply_patch_freeform`.657Disable burst-paste detection in the TUI.

516 658 

517Key659Key

518 660 

519`experimental_use_unified_exec_tool`661`experimental_compact_prompt_file`

520 662 

521Type / Values663Type / Values

522 664 

523`boolean`665`string (path)`

524 666 

525Details667Details

526 668 

527Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`.669Load the compaction prompt override from a file (experimental).

528 670 

529Key671Key

530 672 

531`features.apply_patch_freeform`673`experimental_use_unified_exec_tool`

532 674 

533Type / Values675Type / Values

534 676 

536 678 

537Details679Details

538 680 

539Expose the freeform `apply_patch` tool (experimental).681Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`.

540 682 

541Key683Key

542 684 

552 694 

553Key695Key

554 696 

555`features.apps_mcp_gateway`697`features.codex_hooks`

556 

557Type / Values

558 

559`boolean`

560 

561Details

562 

563Route Apps MCP calls through the OpenAI connectors MCP gateway (`https://api.openai.com/v1/connectors/mcp/`) instead of legacy routing (experimental).

564 

565Key

566 

567`features.child_agents_md`

568 698 

569Type / Values699Type / Values

570 700 

572 702 

573Details703Details

574 704 

575Append AGENTS.md scope/precedence guidance even when no AGENTS.md is present (experimental).705Enable lifecycle hooks loaded from `hooks.json` or inline `[hooks]` config.

576 706 

577Key707Key

578 708 

579`features.collaboration_modes`709`features.enable_request_compression`

580 710 

581Type / Values711Type / Values

582 712 

584 714 

585Details715Details

586 716 

587Enable collaboration modes such as plan mode (stable; on by default).717Compress streaming request bodies with zstd when supported (stable; on by default).

588 718 

589Key719Key

590 720 

591`features.multi_agent`721`features.fast_mode`

592 722 

593Type / Values723Type / Values

594 724 

596 726 

597Details727Details

598 728 

599Enable multi-agent collaboration tools (`spawn\_agent`, `send\_input`, `resume\_agent`, `wait`, and `close\_agent`) (experimental; off by default).729Enable Fast mode selection and the `service_tier = "fast"` path (stable; on by default).

600 730 

601Key731Key

602 732 

603`features.personality`733`features.memories`

604 734 

605Type / Values735Type / Values

606 736 

608 738 

609Details739Details

610 740 

611Enable personality selection controls (stable; on by default).741Enable [Memories](https://developers.openai.com/codex/memories) (off by default).

612 742 

613Key743Key

614 744 

615`features.powershell_utf8`745`features.multi_agent`

616 746 

617Type / Values747Type / Values

618 748 

620 750 

621Details751Details

622 752 

623Force PowerShell UTF-8 output (defaults to true).753Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait_agent`, and `close_agent`) (stable; on by default).

624 754 

625Key755Key

626 756 

627`features.remote_models`757`features.personality`

628 758 

629Type / Values759Type / Values

630 760 

632 762 

633Details763Details

634 764 

635Refresh remote model list before showing readiness (experimental).765Enable personality selection controls (stable; on by default).

636 766 

637Key767Key

638 768 

639`features.request_rule`769`features.prevent_idle_sleep`

640 770 

641Type / Values771Type / Values

642 772 

644 774 

645Details775Details

646 776 

647Enable Smart approvals (`prefix_rule` suggestions on escalation requests; stable; on by default).777Prevent the machine from sleeping while a turn is actively running (experimental; off by default).

648 778 

649Key779Key

650 780 

651`features.runtime_metrics`781`features.shell_snapshot`

652 782 

653Type / Values783Type / Values

654 784 

656 786 

657Details787Details

658 788 

659Show runtime metrics summary in TUI turn separators (experimental).789Snapshot shell environment to speed up repeated commands (stable; on by default).

660 790 

661Key791Key

662 792 

663`features.search_tool`793`features.shell_tool`

664 794 

665Type / Values795Type / Values

666 796 

668 798 

669Details799Details

670 800 

671Enable `search_tool_bm25` for Apps tool discovery before invoking app MCP tools (experimental).801Enable the default `shell` tool for running commands (stable; on by default).

672 802 

673Key803Key

674 804 

675`features.shell_snapshot`805`features.skill_mcp_dependency_install`

676 806 

677Type / Values807Type / Values

678 808 

680 810 

681Details811Details

682 812 

683Snapshot shell environment to speed up repeated commands (beta).813Allow prompting and installing missing MCP dependencies for skills (stable; on by default).

684 814 

685Key815Key

686 816 

687`features.shell_tool`817`features.undo`

688 818 

689Type / Values819Type / Values

690 820 

692 822 

693Details823Details

694 824 

695Enable the default `shell` tool for running commands (stable; on by default).825Enable undo support (stable; off by default).

696 826 

697Key827Key

698 828 

704 834 

705Details835Details

706 836 

707Use the unified PTY-backed exec tool (beta).837Use the unified PTY-backed exec tool (stable; enabled by default except on Windows).

708 

709Key

710 

711`features.use_linux_sandbox_bwrap`

712 

713Type / Values

714 

715`boolean`

716 

717Details

718 

719Use the bubblewrap-based Linux sandbox pipeline (experimental; off by default).

720 838 

721Key839Key

722 840 

840 958 

841Key959Key

842 960 

843`include_apply_patch_tool`961`hooks`

844 962 

845Type / Values963Type / Values

846 964 

847`boolean`965`table`

848 966 

849Details967Details

850 968 

851Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`.969Lifecycle hooks configured inline in `config.toml`. Uses the same event schema as `hooks.json`; see the Hooks guide for examples and supported events.

852 970 

853Key971Key

854 972 

1024 1142 

1025Type / Values1143Type / Values

1026 1144 

1027`array<string>`1145`array<string | { name = string, source = "local" | "remote" }>`

1146 

1147Details

1148 

1149Additional environment variables to whitelist for an MCP stdio server. String entries default to `source = "local"`; use `source = "remote"` only with executor-backed remote stdio.

1150 

1151Key

1152 

1153`mcp_servers.<id>.experimental_environment`

1154 

1155Type / Values

1156 

1157`local | remote`

1028 1158 

1029Details1159Details

1030 1160 

1031Additional environment variables to whitelist for an MCP stdio server.1161Experimental placement for an MCP server. `remote` starts stdio servers through a remote executor environment; streamable HTTP remote placement is not implemented.

1032 1162 

1033Key1163Key

1034 1164 

1044 1174 

1045Key1175Key

1046 1176 

1177`mcp_servers.<id>.oauth_resource`

1178 

1179Type / Values

1180 

1181`string`

1182 

1183Details

1184 

1185Optional RFC 8707 OAuth resource parameter to include during MCP login.

1186 

1187Key

1188 

1047`mcp_servers.<id>.required`1189`mcp_servers.<id>.required`

1048 1190 

1049Type / Values1191Type / Values

1056 1198 

1057Key1199Key

1058 1200 

1201`mcp_servers.<id>.scopes`

1202 

1203Type / Values

1204 

1205`array<string>`

1206 

1207Details

1208 

1209OAuth scopes to request when authenticating to that MCP server.

1210 

1211Key

1212 

1059`mcp_servers.<id>.startup_timeout_ms`1213`mcp_servers.<id>.startup_timeout_ms`

1060 1214 

1061Type / Values1215Type / Values

1104 1258 

1105Key1259Key

1106 1260 

1107`model`1261`memories.consolidation_model`

1108 1262 

1109Type / Values1263Type / Values

1110 1264 

1112 1266 

1113Details1267Details

1114 1268 

1115Model to use (e.g., `gpt-5-codex`).1269Optional model override for global memory consolidation.

1116 1270 

1117Key1271Key

1118 1272 

1119`model_auto_compact_token_limit`1273`memories.disable_on_external_context`

1120 1274 

1121Type / Values1275Type / Values

1122 1276 

1123`number`1277`boolean`

1124 1278 

1125Details1279Details

1126 1280 

1127Token threshold that triggers automatic history compaction (unset uses model defaults).1281When `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`.

1128 1282 

1129Key1283Key

1130 1284 

1131`model_catalog_json`1285`memories.extract_model`

1132 1286 

1133Type / Values1287Type / Values

1134 1288 

1135`string (path)`1289`string`

1136 1290 

1137Details1291Details

1138 1292 

1139Optional path to a JSON model catalog loaded on startup. Profile-level `profiles.<name>.model_catalog_json` can override this per profile.1293Optional model override for per-thread memory extraction.

1140 1294 

1141Key1295Key

1142 1296 

1143`model_context_window`1297`memories.generate_memories`

1144 1298 

1145Type / Values1299Type / Values

1146 1300 

1147`number`1301`boolean`

1148 1302 

1149Details1303Details

1150 1304 

1151Context window tokens available to the active model.1305When `false`, newly created threads are not stored as memory-generation inputs. Defaults to `true`.

1152 1306 

1153Key1307Key

1154 1308 

1155`model_instructions_file`1309`memories.max_raw_memories_for_consolidation`

1156 1310 

1157Type / Values1311Type / Values

1158 1312 

1159`string (path)`1313`number`

1160 1314 

1161Details1315Details

1162 1316 

1163Replacement for built-in instructions instead of `AGENTS.md`.1317Maximum recent raw memories retained for global consolidation. Defaults to `256` and is capped at `4096`.

1164 1318 

1165Key1319Key

1166 1320 

1167`model_provider`1321`memories.max_rollout_age_days`

1168 1322 

1169Type / Values1323Type / Values

1170 1324 

1171`string`1325`number`

1172 1326 

1173Details1327Details

1174 1328 

1175Provider id from `model_providers` (default: `openai`).1329Maximum age of threads considered for memory generation. Defaults to `30` and is clamped to `0`-`90`.

1176 1330 

1177Key1331Key

1178 1332 

1179`model_providers.<id>.base_url`1333`memories.max_rollouts_per_startup`

1180 1334 

1181Type / Values1335Type / Values

1182 1336 

1183`string`1337`number`

1184 1338 

1185Details1339Details

1186 1340 

1187API base URL for the model provider.1341Maximum rollout candidates processed per startup pass. Defaults to `16` and is capped at `128`.

1188 1342 

1189Key1343Key

1190 1344 

1191`model_providers.<id>.env_http_headers`1345`memories.max_unused_days`

1192 1346 

1193Type / Values1347Type / Values

1194 1348 

1195`map<string,string>`1349`number`

1196 1350 

1197Details1351Details

1198 1352 

1199HTTP headers populated from environment variables when present.1353Maximum days since a memory was last used before it becomes ineligible for consolidation. Defaults to `30` and is clamped to `0`-`365`.

1200 1354 

1201Key1355Key

1202 1356 

1203`model_providers.<id>.env_key`1357`memories.min_rollout_idle_hours`

1204 1358 

1205Type / Values1359Type / Values

1206 1360 

1207`string`1361`number`

1208 1362 

1209Details1363Details

1210 1364 

1211Environment variable supplying the provider API key.1365Minimum idle time before a thread is considered for memory generation. Defaults to `6` and is clamped to `1`-`48`.

1212 1366 

1213Key1367Key

1214 1368 

1215`model_providers.<id>.env_key_instructions`1369`memories.use_memories`

1216 1370 

1217Type / Values1371Type / Values

1218 1372 

1219`string`1373`boolean`

1220 1374 

1221Details1375Details

1222 1376 

1223Optional setup guidance for the provider API key.1377When `false`, Codex skips injecting existing memories into future sessions. Defaults to `true`.

1224 1378 

1225Key1379Key

1226 1380 

1227`model_providers.<id>.experimental_bearer_token`1381`model`

1228 1382 

1229Type / Values1383Type / Values

1230 1384 

1232 1386 

1233Details1387Details

1234 1388 

1235Direct bearer token for the provider (discouraged; use `env_key`).1389Model to use (e.g., `gpt-5.5`).

1236 1390 

1237Key1391Key

1238 1392 

1239`model_providers.<id>.http_headers`1393`model_auto_compact_token_limit`

1240 1394 

1241Type / Values1395Type / Values

1242 1396 

1243`map<string,string>`1397`number`

1244 1398 

1245Details1399Details

1246 1400 

1247Static HTTP headers added to provider requests.1401Token threshold that triggers automatic history compaction (unset uses model defaults).

1248 1402 

1249Key1403Key

1250 1404 

1251`model_providers.<id>.name`1405`model_catalog_json`

1252 1406 

1253Type / Values1407Type / Values

1254 1408 

1255`string`1409`string (path)`

1256 1410 

1257Details1411Details

1258 1412 

1259Display name for a custom model provider.1413Optional path to a JSON model catalog loaded on startup. Profile-level `profiles.<name>.model_catalog_json` can override this per profile.

1260 1414 

1261Key1415Key

1262 1416 

1263`model_providers.<id>.query_params`1417`model_context_window`

1264 1418 

1265Type / Values1419Type / Values

1266 1420 

1267`map<string,string>`1421`number`

1268 1422 

1269Details1423Details

1270 1424 

1271Extra query parameters appended to provider requests.1425Context window tokens available to the active model.

1272 1426 

1273Key1427Key

1274 1428 

1275`model_providers.<id>.request_max_retries`1429`model_instructions_file`

1276 1430 

1277Type / Values1431Type / Values

1278 1432 

1279`number`1433`string (path)`

1280 1434 

1281Details1435Details

1282 1436 

1283Retry count for HTTP requests to the provider (default: 4).1437Replacement for built-in instructions instead of `AGENTS.md`.

1284 1438 

1285Key1439Key

1286 1440 

1287`model_providers.<id>.requires_openai_auth`1441`model_provider`

1288 1442 

1289Type / Values1443Type / Values

1290 1444 

1291`boolean`1445`string`

1292 1446 

1293Details1447Details

1294 1448 

1295The provider uses OpenAI authentication (defaults to false).1449Provider id from `model_providers` (default: `openai`).

1296 1450 

1297Key1451Key

1298 1452 

1299`model_providers.<id>.stream_idle_timeout_ms`1453`model_providers.<id>`

1300 1454 

1301Type / Values1455Type / Values

1302 1456 

1303`number`1457`table`

1304 1458 

1305Details1459Details

1306 1460 

1307Idle timeout for SSE streams in milliseconds (default: 300000).1461Custom provider definition. Built-in provider IDs (`openai`, `ollama`, and `lmstudio`) are reserved and cannot be overridden.

1308 1462 

1309Key1463Key

1310 1464 

1311`model_providers.<id>.stream_max_retries`1465`model_providers.<id>.auth`

1312 1466 

1313Type / Values1467Type / Values

1314 1468 

1315`number`1469`table`

1316 1470 

1317Details1471Details

1318 1472 

1319Retry count for SSE streaming interruptions (default: 5).1473Command-backed bearer token configuration for a custom provider. Do not combine with `env_key`, `experimental_bearer_token`, or `requires_openai_auth`.

1320 1474 

1321Key1475Key

1322 1476 

1323`model_providers.<id>.wire_api`1477`model_providers.<id>.auth.args`

1324 1478 

1325Type / Values1479Type / Values

1326 1480 

1327`chat | responses`1481`array<string>`

1328 1482 

1329Details1483Details

1330 1484 

1331Protocol used by the provider (defaults to `chat` if omitted).1485Arguments passed to the token command.

1332 1486 

1333Key1487Key

1334 1488 

1335`model_reasoning_effort`1489`model_providers.<id>.auth.command`

1336 1490 

1337Type / Values1491Type / Values

1338 1492 

1339`minimal | low | medium | high | xhigh`1493`string`

1340 1494 

1341Details1495Details

1342 1496 

1343Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent).1497Command to run when Codex needs a bearer token. The command must print the token to stdout.

1344 1498 

1345Key1499Key

1346 1500 

1347`model_reasoning_summary`1501`model_providers.<id>.auth.cwd`

1348 1502 

1349Type / Values1503Type / Values

1350 1504 

1351`auto | concise | detailed | none`1505`string (path)`

1352 1506 

1353Details1507Details

1354 1508 

1355Select reasoning summary detail or disable summaries entirely.1509Working directory for the token command.

1356 1510 

1357Key1511Key

1358 1512 

1359`model_supports_reasoning_summaries`1513`model_providers.<id>.auth.refresh_interval_ms`

1360 1514 

1361Type / Values1515Type / Values

1362 1516 

1363`boolean`1517`number`

1364 1518 

1365Details1519Details

1366 1520 

1367Force Codex to send or not send reasoning metadata.1521How often Codex proactively refreshes the token in milliseconds (default: 300000). Set to `0` to refresh only after an authentication retry.

1368 1522 

1369Key1523Key

1370 1524 

1371`model_verbosity`1525`model_providers.<id>.auth.timeout_ms`

1372 1526 

1373Type / Values1527Type / Values

1374 1528 

1375`low | medium | high`1529`number`

1376 1530 

1377Details1531Details

1378 1532 

1379Control GPT-5 Responses API verbosity (defaults to `medium`).1533Maximum token command runtime in milliseconds (default: 5000).

1380 1534 

1381Key1535Key

1382 1536 

1383`notice.hide_full_access_warning`1537`model_providers.<id>.base_url`

1538 

1539Type / Values

1540 

1541`string`

1542 

1543Details

1544 

1545API base URL for the model provider.

1546 

1547Key

1548 

1549`model_providers.<id>.env_http_headers`

1550 

1551Type / Values

1552 

1553`map<string,string>`

1554 

1555Details

1556 

1557HTTP headers populated from environment variables when present.

1558 

1559Key

1560 

1561`model_providers.<id>.env_key`

1562 

1563Type / Values

1564 

1565`string`

1566 

1567Details

1568 

1569Environment variable supplying the provider API key.

1570 

1571Key

1572 

1573`model_providers.<id>.env_key_instructions`

1574 

1575Type / Values

1576 

1577`string`

1578 

1579Details

1580 

1581Optional setup guidance for the provider API key.

1582 

1583Key

1584 

1585`model_providers.<id>.experimental_bearer_token`

1586 

1587Type / Values

1588 

1589`string`

1590 

1591Details

1592 

1593Direct bearer token for the provider (discouraged; use `env_key`).

1594 

1595Key

1596 

1597`model_providers.<id>.http_headers`

1598 

1599Type / Values

1600 

1601`map<string,string>`

1602 

1603Details

1604 

1605Static HTTP headers added to provider requests.

1606 

1607Key

1608 

1609`model_providers.<id>.name`

1610 

1611Type / Values

1612 

1613`string`

1614 

1615Details

1616 

1617Display name for a custom model provider.

1618 

1619Key

1620 

1621`model_providers.<id>.query_params`

1622 

1623Type / Values

1624 

1625`map<string,string>`

1626 

1627Details

1628 

1629Extra query parameters appended to provider requests.

1630 

1631Key

1632 

1633`model_providers.<id>.request_max_retries`

1634 

1635Type / Values

1636 

1637`number`

1638 

1639Details

1640 

1641Retry count for HTTP requests to the provider (default: 4).

1642 

1643Key

1644 

1645`model_providers.<id>.requires_openai_auth`

1646 

1647Type / Values

1648 

1649`boolean`

1650 

1651Details

1652 

1653The provider uses OpenAI authentication (defaults to false).

1654 

1655Key

1656 

1657`model_providers.<id>.stream_idle_timeout_ms`

1658 

1659Type / Values

1660 

1661`number`

1662 

1663Details

1664 

1665Idle timeout for SSE streams in milliseconds (default: 300000).

1666 

1667Key

1668 

1669`model_providers.<id>.stream_max_retries`

1670 

1671Type / Values

1672 

1673`number`

1674 

1675Details

1676 

1677Retry count for SSE streaming interruptions (default: 5).

1678 

1679Key

1680 

1681`model_providers.<id>.supports_websockets`

1682 

1683Type / Values

1684 

1685`boolean`

1686 

1687Details

1688 

1689Whether that provider supports the Responses API WebSocket transport.

1690 

1691Key

1692 

1693`model_providers.<id>.wire_api`

1694 

1695Type / Values

1696 

1697`responses`

1698 

1699Details

1700 

1701Protocol used by the provider. `responses` is the only supported value, and it is the default when omitted.

1702 

1703Key

1704 

1705`model_reasoning_effort`

1706 

1707Type / Values

1708 

1709`minimal | low | medium | high | xhigh`

1710 

1711Details

1712 

1713Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent).

1714 

1715Key

1716 

1717`model_reasoning_summary`

1718 

1719Type / Values

1720 

1721`auto | concise | detailed | none`