OpenAI - Codex Docs Changes 2026-03-17 00:33 UTC → 2026-04-10 18:23 UTC

81 81 

82If you need Codex to read files, make edits, and run commands with network access without approval prompts, use `--sandbox danger-full-access` (or the `--dangerously-bypass-approvals-and-sandbox` flag). Use caution before doing so.82If you need Codex to read files, make edits, and run commands with network access without approval prompts, use `--sandbox danger-full-access` (or the `--dangerously-bypass-approvals-and-sandbox` flag). Use caution before doing so.

83 83 

84For a middle ground, `approval_policy = { reject = { ... } }` lets you auto-reject specific approval prompt categories (sandbox escalation, execpolicy-rule prompts, or MCP elicitations) while keeping other prompts interactive.84For a middle ground, `approval_policy = { granular = { ... } }` lets you keep specific approval prompt categories interactive while automatically rejecting others. The granular policy covers sandbox approvals, execpolicy-rule prompts, MCP elicitations, `request_permissions` prompts, and skill-script approvals.

85 85 

86### Common sandbox and approval combinations86### Common sandbox and approval combinations

87 87 

111[sandbox_workspace_write]111[sandbox_workspace_write]

112network_access = true112network_access = true

113 113 

114# Optional: granular approval prompt auto-rejection114# Optional: granular approval policy

115# approval_policy = { reject = { sandbox_approval = true, rules = false, mcp_elicitations = false } }115# approval_policy = { granular = {

116# sandbox_approval = true,

117# rules = true,

118# mcp_elicitations = true,

119# request_permissions = false,

120# skill_approval = false

121# } }

116```122```

117 123 

118You can also save presets as profiles, then select them with `codex --profile <name>`:124You can also save presets as profiles, then select them with `codex --profile <name>`:

145Codex enforces the sandbox differently depending on your OS:151Codex enforces the sandbox differently depending on your OS:

146 152 

147- **macOS** uses Seatbelt policies and runs commands using `sandbox-exec` with a profile (`-p`) that corresponds to the `--sandbox` mode you selected. When restricted read access enables platform defaults, Codex appends a curated macOS platform policy (instead of broadly allowing `/System`) to preserve common tool compatibility.153- **macOS** uses Seatbelt policies and runs commands using `sandbox-exec` with a profile (`-p`) that corresponds to the `--sandbox` mode you selected. When restricted read access enables platform defaults, Codex appends a curated macOS platform policy (instead of broadly allowing `/System`) to preserve common tool compatibility.

148- **Linux** uses `Landlock` plus `seccomp` by default. You can opt into the alternative Linux sandbox pipeline with `features.use_linux_sandbox_bwrap = true` (or `-c use_linux_sandbox_bwrap=true`). In managed proxy mode, the bwrap pipeline routes egress through a proxy-only bridge and fails closed if it cannot build valid loopback proxy routes; landlock-only flows do not use that bridge behavior.154- **Linux** uses the bubblewrap pipeline plus `seccomp` by default. `use_legacy_landlock` is available when you need the older path. In managed proxy mode, the default bubblewrap pipeline routes egress through a proxy-only bridge and fails closed if it cannot build valid loopback proxy routes.

149- **Windows** uses the Linux sandbox implementation when running in [Windows Subsystem for Linux (WSL)](https://developers.openai.com/codex/windows#windows-subsystem-for-linux). When running natively on Windows, Codex uses a [Windows sandbox](https://developers.openai.com/codex/windows#windows-sandbox) implementation.155- **Windows** uses the Linux sandbox implementation when running in [Windows Subsystem for Linux (WSL)](https://developers.openai.com/codex/windows#windows-subsystem-for-linux). When running natively on Windows, Codex uses a [Windows sandbox](https://developers.openai.com/codex/windows#windows-sandbox) implementation.

150 156 

151If you use the Codex IDE extension on Windows, it supports WSL directly. Set the following in your VS Code settings to keep the agent inside WSL whenever it’s available:157If you use the Codex IDE extension on Windows, it supports WSL directly. Set the following in your VS Code settings to keep the agent inside WSL whenever it’s available:

163```toml169```toml

164[windows]170[windows]

165sandbox = "unelevated" # or "elevated"171sandbox = "unelevated" # or "elevated"

172# sandbox_private_desktop = true # default; set false only for compatibility

166```173```

167 174 

168See the [Windows setup guide](https://developers.openai.com/codex/windows#windows-sandbox) for details.175See the [Windows setup guide](https://developers.openai.com/codex/windows#windows-sandbox) for details.

21Requests include `method`, `params`, and `id`:21Requests include `method`, `params`, and `id`:

22 22 

23```json23```json

24{ "method": "thread/start", "id": 10, "params": { "model": "gpt-5.1-codex" } }24{ "method": "thread/start", "id": 10, "params": { "model": "gpt-5.4" } }

25```25```

26 26 

27Responses echo the `id` with either `result` or `error`:27Responses echo the `id` with either `result` or `error`:

99 },99 },

100});100});

101send({ method: "initialized", params: {} });101send({ method: "initialized", params: {} });

102send({ method: "thread/start", id: 1, params: { model: "gpt-5.1-codex" } });102send({ method: "thread/start", id: 1, params: { model: "gpt-5.4" } });

103```103```

104 104 

105## Core primitives105## Core primitives

123 123 

124Clients must send a single `initialize` request per transport connection before invoking any other method on that connection, then acknowledge with an `initialized` notification. Requests sent before initialization receive a `Not initialized` error, and repeated `initialize` calls on the same connection return `Already initialized`.124Clients must send a single `initialize` request per transport connection before invoking any other method on that connection, then acknowledge with an `initialized` notification. Requests sent before initialization receive a `Not initialized` error, and repeated `initialize` calls on the same connection return `Already initialized`.

125 125 

126The server returns the user agent string it will present to upstream services. Set `clientInfo` to identify your integration.126The server returns the user agent string it will present to upstream services plus `platformFamily` and `platformOs` values that describe the runtime target. Set `clientInfo` to identify your integration.

127 127 

128`initialize.params.capabilities` also supports per-connection notification opt-out via `optOutNotificationMethods`, which is a list of exact method names to suppress for that connection. Matching is exact (no wildcards/prefixes). Unknown method names are accepted and ignored.128`initialize.params.capabilities` also supports per-connection notification opt-out via `optOutNotificationMethods`, which is a list of exact method names to suppress for that connection. Matching is exact (no wildcards/prefixes). Unknown method names are accepted and ignored.

129 129 

159 },159 },

160 "capabilities": {160 "capabilities": {

161 "experimentalApi": true,161 "experimentalApi": true,

162 "optOutNotificationMethods": [162 "optOutNotificationMethods": ["thread/started", "item/agentMessage/delta"]

163 "codex/event/session_configured",

164 "item/agentMessage/delta"

165 ]

166 }163 }

167 }164 }

168}165}

204- `thread/read` - read a stored thread by id without resuming it; set `includeTurns` to return full turn history. Returned `thread` objects include runtime `status`.201- `thread/read` - read a stored thread by id without resuming it; set `includeTurns` to return full turn history. Returned `thread` objects include runtime `status`.

205- `thread/list` - page through stored thread logs; supports cursor-based pagination plus `modelProviders`, `sourceKinds`, `archived`, and `cwd` filters. Returned `thread` objects include runtime `status`.202- `thread/list` - page through stored thread logs; supports cursor-based pagination plus `modelProviders`, `sourceKinds`, `archived`, and `cwd` filters. Returned `thread` objects include runtime `status`.

206- `thread/loaded/list` - list the thread ids currently loaded in memory.203- `thread/loaded/list` - list the thread ids currently loaded in memory.

204- `thread/name/set` - set or update a thread's user-facing name for a loaded thread or a persisted rollout; emits `thread/name/updated`.

207- `thread/archive` - move a thread's log file into the archived directory; returns `{}` on success and emits `thread/archived`.205- `thread/archive` - move a thread's log file into the archived directory; returns `{}` on success and emits `thread/archived`.

208- `thread/unsubscribe` - unsubscribe this connection from thread turn/item events. If this was the last subscriber, the server unloads the thread and emits `thread/closed`.206- `thread/unsubscribe` - unsubscribe this connection from thread turn/item events. If this was the last subscriber, the server unloads the thread and emits `thread/closed`.

209- `thread/unarchive` - restore an archived thread rollout back into the active sessions directory; returns the restored `thread` and emits `thread/unarchived`.207- `thread/unarchive` - restore an archived thread rollout back into the active sessions directory; returns the restored `thread` and emits `thread/unarchived`.

215- `turn/interrupt` - request cancellation of an in-flight turn; success is `{}` and the turn ends with `status: "interrupted"`.213- `turn/interrupt` - request cancellation of an in-flight turn; success is `{}` and the turn ends with `status: "interrupted"`.

216- `review/start` - kick off the Codex reviewer for a thread; emits `enteredReviewMode` and `exitedReviewMode` items.214- `review/start` - kick off the Codex reviewer for a thread; emits `enteredReviewMode` and `exitedReviewMode` items.

217- `command/exec` - run a single command under the server sandbox without starting a thread/turn.215- `command/exec` - run a single command under the server sandbox without starting a thread/turn.

216- `command/exec/write` - write stdin bytes to a running `command/exec` session or close stdin.

217- `command/exec/resize` - resize a running PTY-backed `command/exec` session.

218- `command/exec/terminate` - terminate a running `command/exec` session.

218- `model/list` - list available models (set `includeHidden: true` to include entries with `hidden: true`) with effort options, optional `upgrade`, and `inputModalities`.219- `model/list` - list available models (set `includeHidden: true` to include entries with `hidden: true`) with effort options, optional `upgrade`, and `inputModalities`.

219- `experimentalFeature/list` - list feature flags with lifecycle stage metadata and cursor pagination.220- `experimentalFeature/list` - list feature flags with lifecycle stage metadata and cursor pagination.

220- `collaborationMode/list` - list collaboration mode presets (experimental, no pagination).221- `collaborationMode/list` - list collaboration mode presets (experimental, no pagination).

221- `skills/list` - list skills for one or more `cwd` values (supports `forceReload` and optional `perCwdExtraUserRoots`).222- `skills/list` - list skills for one or more `cwd` values (supports `forceReload` and optional `perCwdExtraUserRoots`).

223- `plugin/list` - list discovered plugin marketplaces and plugin state, including install/auth policy metadata.

224- `plugin/read` - read one plugin by marketplace path and plugin name, including bundled skills, apps, and MCP server names.

222- `app/list` - list available apps (connectors) with pagination plus accessibility/enabled metadata.225- `app/list` - list available apps (connectors) with pagination plus accessibility/enabled metadata.

223- `skills/config/write` - enable or disable skills by path.226- `skills/config/write` - enable or disable skills by path.

224- `mcpServer/oauth/login` - start an OAuth login for a configured MCP server; returns an authorization URL and emits `mcpServer/oauthLogin/completed` on completion.227- `mcpServer/oauth/login` - start an OAuth login for a configured MCP server; returns an authorization URL and emits `mcpServer/oauthLogin/completed` on completion.

233- `config/value/write` - write a single configuration key/value to the user's `config.toml` on disk.236- `config/value/write` - write a single configuration key/value to the user's `config.toml` on disk.

234- `config/batchWrite` - apply configuration edits atomically to the user's `config.toml` on disk.237- `config/batchWrite` - apply configuration edits atomically to the user's `config.toml` on disk.

235- `configRequirements/read` - fetch requirements from `requirements.toml` and/or MDM, including allow-lists, pinned `featureRequirements`, and residency/network requirements (or `null` if you haven't set any up).238- `configRequirements/read` - fetch requirements from `requirements.toml` and/or MDM, including allow-lists, pinned `featureRequirements`, and residency/network requirements (or `null` if you haven't set any up).

239- `fs/readFile`, `fs/writeFile`, `fs/createDirectory`, `fs/getMetadata`, `fs/readDirectory`, `fs/remove`, and `fs/copy` - operate on absolute filesystem paths through the app-server v2 filesystem API.

236 240 

237## Models241## Models

238 242 

315 319 

316```json320```json

317{ "method": "thread/start", "id": 10, "params": {321{ "method": "thread/start", "id": 10, "params": {

318 "model": "gpt-5.1-codex",322 "model": "gpt-5.4",

319 "cwd": "/Users/me/project",323 "cwd": "/Users/me/project",

320 "approvalPolicy": "never",324 "approvalPolicy": "never",

321 "sandbox": "workspaceWrite",325 "sandbox": "workspaceWrite",

570 "writableRoots": ["/Users/me/project"],574 "writableRoots": ["/Users/me/project"],

571 "networkAccess": true575 "networkAccess": true

572 },576 },

573 "model": "gpt-5.1-codex",577 "model": "gpt-5.4",

574 "effort": "medium",578 "effort": "medium",

575 "summary": "concise",579 "summary": "concise",

576 "personality": "friendly",580 "personality": "friendly",

713- The server rejects empty `command` arrays.717- The server rejects empty `command` arrays.

714- `sandboxPolicy` accepts the same shape used by `turn/start` (for example, `dangerFullAccess`, `readOnly`, `workspaceWrite`, `externalSandbox`).718- `sandboxPolicy` accepts the same shape used by `turn/start` (for example, `dangerFullAccess`, `readOnly`, `workspaceWrite`, `externalSandbox`).

715- When omitted, `timeoutMs` falls back to the server default.719- When omitted, `timeoutMs` falls back to the server default.

720- Set `tty: true` for PTY-backed sessions, and use `processId` when you plan to follow up with `command/exec/write`, `command/exec/resize`, or `command/exec/terminate`.

721- Set `streamStdoutStderr: true` to receive `command/exec/outputDelta` notifications while the command is running.

716 722 

717### Read admin requirements (`configRequirements/read`)723### Read admin requirements (`configRequirements/read`)

718 724 

773 779 

774- Exact-match only: `item/agentMessage/delta` suppresses only that method.780- Exact-match only: `item/agentMessage/delta` suppresses only that method.

775- Unknown method names are ignored.781- Unknown method names are ignored.

776- Applies to both legacy (`codex/event/*`) and v2 (`thread/*`, `turn/*`, `item/*`, etc.) notifications.782- Applies to the current `thread/*`, `turn/*`, `item/*`, and related v2 notifications.

777- Doesn't apply to requests, responses, or errors.783- Doesn't apply to requests, responses, or errors.

778 784 

779### Fuzzy file search events (experimental)785### Fuzzy file search events (experimental)

1# Windows1# Windows

2 2 

3The [Codex app for Windows](https://apps.microsoft.com/detail/9plm9xgg6vks?hl=en-US&gl=US) gives you one interface for3The [Codex app for Windows](https://get.microsoft.com/installer/download/9PLM9XGG6VKS?cid=website_cta_psi) gives you one interface for

4working across projects, running parallel agent threads, and reviewing results.4working across projects, running parallel agent threads, and reviewing results.

5It runs natively on Windows using PowerShell and the5It runs natively on Windows using PowerShell and the

6[Windows sandbox](https://developers.openai.com/codex/windows#windows-sandbox), or you can configure it to6[Windows sandbox](https://developers.openai.com/codex/windows#windows-sandbox), or you can configure it to

11## Download and update the Codex app11## Download and update the Codex app

12 12 

13Download the Codex app from the13Download the Codex app from the

14[Microsoft Store](https://apps.microsoft.com/detail/9plm9xgg6vks?hl=en-US&gl=US).14[Microsoft Store](https://get.microsoft.com/installer/download/9PLM9XGG6VKS?cid=website_cta_psi).

15 15 

16Then follow the [quickstart](https://developers.openai.com/codex/quickstart?setup=app) to get started.16Then follow the [quickstart](https://developers.openai.com/codex/quickstart?setup=app) to get started.

17 17 

91 91 

92These settings are commonly applied via managed configuration rather than per-user setup. See [Managed configuration](https://developers.openai.com/codex/enterprise/managed-configuration).92These settings are commonly applied via managed configuration rather than per-user setup. See [Managed configuration](https://developers.openai.com/codex/enterprise/managed-configuration).

93 93 

94## Login diagnostics

95 

96Direct `codex login` runs write a dedicated `codex-login.log` file under

97your configured log directory. Use it when you need to debug browser-login or

98device-code failures, or when support asks for login-specific logs.

99 

100## Custom CA bundles

101 

102If your network uses a corporate TLS proxy or private root CA, set

103`CODEX_CA_CERTIFICATE` to a PEM bundle before logging in. When

104`CODEX_CA_CERTIFICATE` is unset, Codex falls back to `SSL_CERT_FILE`. The same

105custom CA settings apply to login, normal HTTPS requests, and secure websocket

106connections.

107 

108```shell

109export CODEX_CA_CERTIFICATE=/path/to/corporate-root-ca.pem

110codex login

111```

112 

94## Login on headless devices113## Login on headless devices

95 114 

96If you are signing in to ChatGPT with the Codex CLI, there are some situations where the browser-based login UI may not work:115If you are signing in to ChatGPT with the Codex CLI, there are some situations where the browser-based login UI may not work:

69 69 

70Launch a Codex Cloud task, choose environments, and apply the resulting diffs without leaving your terminal.](https://developers.openai.com/codex/cli/features#working-with-codex-cloud)[### Scripting Codex70Launch a Codex Cloud task, choose environments, and apply the resulting diffs without leaving your terminal.](https://developers.openai.com/codex/cli/features#working-with-codex-cloud)[### Scripting Codex

71 71 

72Automate repeatable workflows by scripting Codex with the `exec` command.](https://developers.openai.com/codex/sdk#using-codex-cli-programmatically)[### Model Context Protocol72Automate repeatable workflows by scripting Codex with the `exec` command.](https://developers.openai.com/codex/noninteractive)[### Model Context Protocol

73 73 

74Give Codex access to additional third-party tools and context with Model Context Protocol (MCP).](https://developers.openai.com/codex/mcp)[### Approval modes74Give Codex access to additional third-party tools and context with Model Context Protocol (MCP).](https://developers.openai.com/codex/mcp)[### Approval modes

75 75 

46 46 

47## Models and reasoning47## Models and reasoning

48 48 

49For most tasks in Codex, `gpt-5.4` is the recommended model. It brings the industry-leading coding capabilities of `gpt-5.3-codex` to OpenAI’s flagship frontier model, combining frontier coding performance with stronger reasoning, native computer use, and broader professional workflows. For extra fast tasks, ChatGPT Pro subscribers have access to the GPT-5.3-Codex-Spark model in research preview.49For most tasks in Codex, `gpt-5.4` is the recommended model. It brings the

50industry-leading coding capabilities of `gpt-5.3-codex` to OpenAI’s flagship

51frontier model, combining frontier coding performance with stronger reasoning,

52native computer use, and broader professional workflows. For extra fast tasks,

53ChatGPT Pro subscribers have access to the GPT-5.3-Codex-Spark model in

54research preview.

50 55 

51Switch models mid-session with the `/model` command, or specify one when launching the CLI.56Switch models mid-session with the `/model` command, or specify one when launching the CLI.

52 57 

22| `--enable` | `feature` | Force-enable a feature flag (translates to `-c features.<name>=true`). Repeatable. |22| `--enable` | `feature` | Force-enable a feature flag (translates to `-c features.<name>=true`). Repeatable. |

23| `--full-auto` | `boolean` | Shortcut for low-friction local work: sets `--ask-for-approval on-request` and `--sandbox workspace-write`. |23| `--full-auto` | `boolean` | Shortcut for low-friction local work: sets `--ask-for-approval on-request` and `--sandbox workspace-write`. |

24| `--image, -i` | `path[,path...]` | Attach one or more image files to the initial prompt. Separate multiple paths with commas or repeat the flag. |24| `--image, -i` | `path[,path...]` | Attach one or more image files to the initial prompt. Separate multiple paths with commas or repeat the flag. |

25| `--model, -m` | `string` | Override the model set in configuration (for example `gpt-5-codex`). |25| `--model, -m` | `string` | Override the model set in configuration (for example `gpt-5.4`). |

26| `--no-alt-screen` | `boolean` | Disable alternate screen mode for the TUI (overrides `tui.alternate_screen` for this run). |26| `--no-alt-screen` | `boolean` | Disable alternate screen mode for the TUI (overrides `tui.alternate_screen` for this run). |

27| `--oss` | `boolean` | Use the local open source model provider (equivalent to `-c model_provider="oss"`). Validates that Ollama is running. |27| `--oss` | `boolean` | Use the local open source model provider (equivalent to `-c model_provider="oss"`). Validates that Ollama is running. |

28| `--profile, -p` | `string` | Configuration profile name to load from `~/.codex/config.toml`. |28| `--profile, -p` | `string` | Configuration profile name to load from `~/.codex/config.toml`. |

148 148 

149Details149Details

150 150 

151Override the model set in configuration (for example `gpt-5-codex`).151Override the model set in configuration (for example `gpt-5.4`).

152 152 

153Key153Key

154 154 

8This guide shows you how to:8This guide shows you how to:

9 9 

10- Find the right built-in slash command for a task10- Find the right built-in slash command for a task

11- Steer an active session with commands like `/model`, `/personality`,11- Steer an active session with commands like `/model`, `/fast`,

12 `/permissions`, `/experimental`, `/agent`, and `/status`12 `/personality`, `/permissions`, `/agent`, and `/status`

13 13 

14## Built-in slash commands14## Built-in slash commands

15 15 

22| [`/sandbox-add-read-dir`](#grant-sandbox-read-access-with-sandbox-add-read-dir) | Grant sandbox read access to an extra directory (Windows only). | Unblock commands that need to read an absolute directory path outside the current readable roots. |22| [`/sandbox-add-read-dir`](#grant-sandbox-read-access-with-sandbox-add-read-dir) | Grant sandbox read access to an extra directory (Windows only). | Unblock commands that need to read an absolute directory path outside the current readable roots. |

23| [`/agent`](#switch-agent-threads-with-agent) | Switch the active agent thread. | Inspect or continue work in a spawned subagent thread. |23| [`/agent`](#switch-agent-threads-with-agent) | Switch the active agent thread. | Inspect or continue work in a spawned subagent thread. |

24| [`/apps`](#browse-apps-with-apps) | Browse apps (connectors) and insert them into your prompt. | Attach an app as `$app-slug` before asking Codex to use it. |24| [`/apps`](#browse-apps-with-apps) | Browse apps (connectors) and insert them into your prompt. | Attach an app as `$app-slug` before asking Codex to use it. |

25| [`/clear`](#clear-the-terminal-and-start-a-new-chat-with-clear) | Clear the terminal and start a fresh chat. | Reset the visible UI and conversation together when you want to start over. |25| [`/clear`](#clear-the-terminal-and-start-a-new-chat-with-clear) | Clear the terminal and start a fresh chat. | Reset the visible UI and conversation together when you want a clean slate. |

26| [`/compact`](#keep-transcripts-lean-with-compact) | Summarize the visible conversation to free tokens. | Use after long runs so Codex retains key points without blowing the context window. |26| [`/compact`](#keep-transcripts-lean-with-compact) | Summarize the visible conversation to free tokens. | Use after long runs so Codex retains key points without blowing the context window. |

27| [`/copy`](#copy-the-latest-response-with-copy) | Copy the latest completed Codex output. | Grab the latest finished response or plan text without manually selecting it. |27| [`/copy`](#copy-the-latest-response-with-copy) | Copy the latest completed Codex output. | Grab the latest finished response or plan text without manually selecting it. |

28| [`/diff`](#review-changes-with-diff) | Show the Git diff, including files Git isn't tracking yet. | Review Codex's edits before you commit or run tests. |28| [`/diff`](#review-changes-with-diff) | Show the Git diff, including files Git isn't tracking yet. | Review Codex's edits before you commit or run tests. |

34| [`/mcp`](#list-mcp-tools-with-mcp) | List configured Model Context Protocol (MCP) tools. | Check which external tools Codex can call during the session. |34| [`/mcp`](#list-mcp-tools-with-mcp) | List configured Model Context Protocol (MCP) tools. | Check which external tools Codex can call during the session. |

35| [`/mention`](#highlight-files-with-mention) | Attach a file to the conversation. | Point Codex at specific files or folders you want it to inspect next. |35| [`/mention`](#highlight-files-with-mention) | Attach a file to the conversation. | Point Codex at specific files or folders you want it to inspect next. |

36| [`/model`](#set-the-active-model-with-model) | Choose the active model (and reasoning effort, when available). | Switch between general-purpose models (`gpt-4.1-mini`) and deeper reasoning models before running a task. |36| [`/model`](#set-the-active-model-with-model) | Choose the active model (and reasoning effort, when available). | Switch between general-purpose models (`gpt-4.1-mini`) and deeper reasoning models before running a task. |

37| [`/fast`](#toggle-fast-mode-with-fast) | Toggle Fast mode for GPT-5.4. | Turn Fast mode on or off, or check whether the current thread is using it. |

37| [`/plan`](#switch-to-plan-mode-with-plan) | Switch to plan mode and optionally send a prompt. | Ask Codex to propose an execution plan before implementation work starts. |38| [`/plan`](#switch-to-plan-mode-with-plan) | Switch to plan mode and optionally send a prompt. | Ask Codex to propose an execution plan before implementation work starts. |

38| [`/personality`](#set-a-communication-style-with-personality) | Choose a communication style for responses. | Make Codex more concise, more explanatory, or more collaborative without changing your instructions. |39| [`/personality`](#set-a-communication-style-with-personality) | Choose a communication style for responses. | Make Codex more concise, more explanatory, or more collaborative without changing your instructions. |

39| [`/ps`](#check-background-terminals-with-ps) | Show experimental background terminals and their recent output. | Check long-running commands without leaving the main transcript. |40| [`/ps`](#check-background-terminals-with-ps) | Show experimental background terminals and their recent output. | Check long-running commands without leaving the main transcript. |

63 64 

64Expected: Codex confirms the new model in the transcript. Run `/status` to verify the change.65Expected: Codex confirms the new model in the transcript. Run `/status` to verify the change.

65 66 

67### Toggle Fast mode with `/fast`

68 

691. Type `/fast on`, `/fast off`, or `/fast status`.

702. If you want the setting to persist, confirm the update when Codex offers to save it.

71 

72Expected: Codex reports whether Fast mode is on or off for the current thread. In the TUI footer, you can also show a Fast mode status-line item with `/statusline`.

73 

66### Set a communication style with `/personality`74### Set a communication style with `/personality`

67 75 

68Use `/personality` to change how Codex communicates without rewriting your prompt.76Use `/personality` to change how Codex communicates without rewriting your prompt.

92### Toggle experimental features with `/experimental`100### Toggle experimental features with `/experimental`

93 101 

941. Type `/experimental` and press Enter.1021. Type `/experimental` and press Enter.

952. Toggle the features you want, then restart Codex.1032. Toggle the features you want (for example, Apps or Smart Approvals), then restart Codex if the prompt asks you to.

96 104 

97Expected: Codex saves your feature choices to config and applies them on restart.105Expected: Codex saves your feature choices to config and applies them on restart.

98 106 

209Expected: Codex starts a fresh conversation in the same CLI session, so you217Expected: Codex starts a fresh conversation in the same CLI session, so you

210can switch tasks without leaving your terminal.218can switch tasks without leaving your terminal.

211 219 

212Unlike `/clear`, `/new` doesn’t clear the current terminal view first.220Unlike `/clear`, `/new` does not clear the current terminal view first.

213 221 

214### Resume a saved conversation with `/resume`222### Resume a saved conversation with `/resume`

215 223 

22 22 

23 Learn more](https://developers.openai.com/codex/explore) [### Community23 Learn more](https://developers.openai.com/codex/explore) [### Community

24 24 

25Explore Codex Ambassadors and upcoming community meetups by location.25Read community posts, explore meetups, and connect with Codex builders.

26 26 

27 See community](https://developers.openai.com/codex/community/meetups) [### Codex for OSS27 See community](/community) [### Codex for Open Source

28 28 

29Apply or nominate maintainers for API credits, ChatGPT Pro with Codex, and selective Codex Security access.29Apply or nominate maintainers for API credits, ChatGPT Pro with Codex, and selective Codex Security access.

30 30 

31 Learn more](https://developers.openai.com/codex/community/codex-for-oss)31 Learn more](https://developers.openai.com/community/codex-for-oss)

1# Codex for Open Source Program Terms1# Codex for Open Source Program Terms

2 2 

3These Program Terms govern the Codex for Open Source program (the “Program”) offered by OpenAI OpCo, LLC and its affiliates (“OpenAI,” “we,” “our,” or “us”). By submitting an application to the Program or accepting any Program benefit, you agree to these Program Terms.3These Program Terms govern the Codex for OSS program (the "Program") offered by OpenAI OpCo, LLC and its affiliates ("OpenAI," "we," "our," or "us"). By submitting an application to the Program or accepting any Program benefit, you agree to these Program Terms.

4 4 

5These Program Terms supplement, and do not replace, the OpenAI Terms of Use, Privacy Policy, applicable service terms, and OpenAI policies that govern your use of ChatGPT, Codex, the API, and any other OpenAI services made available through the Program. If there is a conflict, these Program Terms control only with respect to the Program.5These Program Terms supplement, and do not replace, the OpenAI Terms of Use, Privacy Policy, applicable service terms, and OpenAI policies that govern your use of ChatGPT, Codex, the API, and any other OpenAI services made available through the Program. If there is a conflict, these Program Terms control only with respect to the Program.

6 6 

54Skills are often the best fit for reusable workflows because they support richer instructions, scripts, and references while staying reusable across tasks.54Skills are often the best fit for reusable workflows because they support richer instructions, scripts, and references while staying reusable across tasks.

55Skills are loaded and visible to the agent (at least their metadata), so Codex can discover and choose them implicitly. This keeps rich workflows available without bloating context up front.55Skills are loaded and visible to the agent (at least their metadata), so Codex can discover and choose them implicitly. This keeps rich workflows available without bloating context up front.

56 56 

57Use skill folders to author and iterate on workflows locally. If a plugin

58already exists for the workflow, install it first to reuse a proven setup. When

59you want to distribute your own workflow across teams or bundle it with app

60integrations, package it as a [plugin](https://developers.openai.com/codex/plugins/build). Skills remain the

61authoring format; plugins are the installable distribution unit.

62 

57A skill is typically a `SKILL.md` file plus optional scripts, references, and assets.63A skill is typically a `SKILL.md` file plus optional scripts, references, and assets.

58 64 

59- my-skill/65- my-skill/

87 93 

88Skills can be global (in your user directory, for you as a developer) or repo-specific (checked into `.agents/skills`, for your team). Put repo skills in `.agents/skills` when the workflow applies to that project; use your user directory for skills you want across all repos.94Skills can be global (in your user directory, for you as a developer) or repo-specific (checked into `.agents/skills`, for your team). Put repo skills in `.agents/skills` when the workflow applies to that project; use your user directory for skills you want across all repos.

89 95 

90| Layer | Global | repo |96| Layer | Global | Repo |

91| :----- | :--------------------- | :--------------------------------------------- |97| :----- | :--------------------- | :--------------------------------------------- |

92| AGENTS | `~/.codex/AGENTS.md` | `AGENTS.md` in repo root or nested directories |98| AGENTS | `~/.codex/AGENTS.md` | `AGENTS.md` in repo root or nested directories |

93| Skills | `$HOME/.agents/skills` | `.agents/skills` in repo |99| Skills | `$HOME/.agents/skills` | `.agents/skills` in repo |

145Build in this order:151Build in this order:

146 152 

1471. [Custom instructions with AGENTS.md](https://developers.openai.com/codex/guides/agents-md) so Codex follows your repo conventions. Add pre-commit hooks and linters to enforce those rules.1531. [Custom instructions with AGENTS.md](https://developers.openai.com/codex/guides/agents-md) so Codex follows your repo conventions. Add pre-commit hooks and linters to enforce those rules.

1482. [Skills](https://developers.openai.com/codex/skills) so you never have the same conversation twice. Skills can include a `scripts/` directory with CLI scripts or pair with [MCP](https://developers.openai.com/codex/mcp) for external systems.1542. Install a [plugin](https://developers.openai.com/codex/plugins) when a reusable workflow already exists. Otherwise, create a [skill](https://developers.openai.com/codex/skills) and package it as a plugin when you want to share it.

1493. [MCP](https://developers.openai.com/codex/mcp) when workflows need external systems (Linear, GitHub, docs servers, design tools).1553. [MCP](https://developers.openai.com/codex/mcp) when workflows need external systems (Linear, GitHub, docs servers, design tools).

1504. [Subagents](https://developers.openai.com/codex/subagents) when you're ready to delegate noisy or specialized tasks to subagents.1564. [Subagents](https://developers.openai.com/codex/subagents) when you're ready to delegate noisy or specialized tasks to subagents.

36inside enforced limits. That makes it easier to let Codex work independently36inside enforced limits. That makes it easier to let Codex work independently

37while still knowing when it will stop and ask for help.37while still knowing when it will stop and ask for help.

38 38 

39## Getting started

40 

41Codex applies sandboxing automatically when you use the default permissions

42mode.

43 

44### Prerequisites

45 

46On **macOS**, sandboxing works out of the box using the built-in Seatbelt

47framework.

48 

49On **Windows**, Codex uses the native [Windows

50sandbox](https://developers.openai.com/codex/windows#windows-sandbox) when you run in PowerShell and the

51Linux sandbox implementation when you run in WSL2.

52 

53On **Linux and WSL2**, install `bubblewrap` with your package manager first:

54 

55```bash

56sudo apt install bubblewrap

57```

58 

59```bash

60sudo dnf install bubblewrap

61```

62 

63Codex uses the system `bwrap` at `/usr/bin/bwrap` when it is available. If it

64is missing, Codex falls back to a bundled helper, but that helper requires

65unprivileged user namespaces. Installing your distro’s `bubblewrap` package is

66the most reliable setup.

67 

68Codex surfaces a startup warning when `bwrap` is missing or cannot create user

69namespaces. On distributions that restrict them with AppArmor, you can enable

70them with:

71 

72```bash

73sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0

74```

75 

39## How you control it76## How you control it

40 77 

41Most people start with the permissions controls in the product.78Most people start with the permissions controls in the product.

1# Subagents1# Subagents

2 2 

3Codex can run subagent workflows by spawning specialized agents in parallel so3Codex can run subagent workflows by spawning specialized agents in parallel so

4they can explore, execute, or analyze work concurrently.4they can explore, tackle, or analyze work concurrently.

5 5 

6This page explains the core concepts and tradeoffs. For setup, agent configuration, and examples, see [Subagents](https://developers.openai.com/codex/subagents).6This page explains the core concepts and tradeoffs. For setup, agent configuration, and examples, see [Subagents](https://developers.openai.com/codex/subagents).

7 7 

65 65 

66If you don't pin a model or `model_reasoning_effort`, Codex can choose a setup66If you don't pin a model or `model_reasoning_effort`, Codex can choose a setup

67that balances intelligence, speed, and price for the task. It may favor67that balances intelligence, speed, and price for the task. It may favor

68`gpt-5.3-codex-spark` for fast scans or a higher-effort `gpt-5.4`68`gpt-5.4-mini` for fast scans or a higher-effort `gpt-5.4`

69configuration for harder reasoning. When you want finer control, steer that69configuration for more demanding reasoning. When you want finer control, steer that

70choice in your prompt or set `model` and `model_reasoning_effort` directly in70choice in your prompt or set `model` and `model_reasoning_effort` directly in

71the agent file.71the agent file.

72 72 

73For most tasks in Codex, start with `gpt-5.4`. Use `gpt-5.3-codex-spark` when73For most tasks in Codex, start with `gpt-5.4`. Use `gpt-5.4-mini` when you

74you want a faster option for lighter subagent work.74want a faster, lower-cost option for lighter subagent work. If you have

75ChatGPT Pro and want near-instant text-only iteration, `gpt-5.3-codex-spark`

76remains available in research preview.

75 77 

76### Model choice78### Model choice

77 79 

78- **`gpt-5.4`**: Start here for most agents. It combines strong coding, reasoning, tool use, and broader workflows. The main agent and agents that coordinate ambiguous or multi-step work fit here.80- **`gpt-5.4`**: Start here for most agents. It combines strong coding, reasoning, tool use, and broader workflows. The main agent and agents that coordinate ambiguous or multi-step work fit here.

79- **`gpt-5.3-codex-spark`**: Use for agents that favor speed over depth, such as exploration, read-heavy scans, or quick summarization tasks. It works well for parallel workers that return distilled results to the main agent.81- **`gpt-5.4-mini`**: Use for agents that favor speed and efficiency over depth, such as exploration, read-heavy scans, large-file review, or processing supporting documents. It works well for parallel workers that return distilled results to the main agent.

82- **`gpt-5.3-codex-spark`**: If you have ChatGPT Pro, use this research preview model for near-instant, text-only iteration when latency matters more than broader capability.

80 83 

81### Reasoning effort (`model_reasoning_effort`)84### Reasoning effort (`model_reasoning_effort`)

82 85 

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

16 16 

17```toml17```toml

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

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

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

21 21 

74 74 

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

76 76 

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

78 78 

79```toml79```toml

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

81codex

82```81```

83 82 

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

87 86 

88For security, Codex loads project-scoped config files only when the project is trusted. If the project is untrusted, Codex ignores `.codex/config.toml` files in the project.87For security, Codex loads project-scoped config files only when the project is trusted. If the project is untrusted, Codex ignores `.codex/config.toml` files in the project.

89 88 

90Relative paths inside a project config (for example, `experimental_instructions_file`) are resolved relative to the `.codex/` folder that contains the `config.toml`.89Relative paths inside a project config (for example, `model_instructions_file`) are resolved relative to the `.codex/` folder that contains the `config.toml`.

90 

91## Hooks (experimental)

92 

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

94active config layers.

95 

96In practice, the two most useful locations are:

97 

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

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

100 

101Turn hooks on with:

102 

103```toml

104[features]

105codex_hooks = true

106```

107 

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

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

91 110 

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

93 112 

113Define additional providers and point `model_provider` at them:132Define additional providers and point `model_provider` at them:

114 133 

115```toml134```toml

116model = "gpt-5.1"135model = "gpt-5.4"

117model_provider = "proxy"136model_provider = "proxy"

118 137 

119[model_providers.proxy]138[model_providers.proxy]

192 211 

193For operational details to keep in mind while editing `config.toml`, see [Common sandbox and approval combinations](https://developers.openai.com/codex/agent-approvals-security#common-sandbox-and-approval-combinations), [Protected paths in writable roots](https://developers.openai.com/codex/agent-approvals-security#protected-paths-in-writable-roots), and [Network access](https://developers.openai.com/codex/agent-approvals-security#network-access).212For operational details to keep in mind while editing `config.toml`, see [Common sandbox and approval combinations](https://developers.openai.com/codex/agent-approvals-security#common-sandbox-and-approval-combinations), [Protected paths in writable roots](https://developers.openai.com/codex/agent-approvals-security#protected-paths-in-writable-roots), and [Network access](https://developers.openai.com/codex/agent-approvals-security#network-access).

194 213 

195You can also use a granular reject policy (`approval_policy = { reject = { ... } }`) to auto-reject only selected prompt categories, such as sandbox approvals, `execpolicy` rule prompts, or MCP input requests (`mcp_elicitations`), while keeping other prompts interactive.214You can also use a granular approval policy (`approval_policy = { granular = { ... } }`) to allow or auto-reject individual prompt categories. This is useful when you want normal interactive approvals for some cases but want others, such as `request_permissions` or skill-script prompts, to fail closed automatically.

196 215 

197```216```

198approval_policy = "untrusted" # Other options: on-request, never, or { reject = { ... } }217approval_policy = "untrusted" # Other options: on-request, never, or { granular = { ... } }

199sandbox_mode = "workspace-write"218sandbox_mode = "workspace-write"

200allow_login_shell = false # Optional hardening: disallow login shells for shell tools219allow_login_shell = false # Optional hardening: disallow login shells for shell tools

201 220 

221# Example granular approval policy:

222# approval_policy = { granular = {

223# sandbox_approval = true,

224# rules = true,

225# mcp_elicitations = true,

226# request_permissions = false,

227# skill_approval = false

228# } }

229 

202[sandbox_workspace_write]230[sandbox_workspace_write]

203exclude_tmpdir_env_var = false # Allow $TMPDIR231exclude_tmpdir_env_var = false # Allow $TMPDIR

204exclude_slash_tmp = false # Allow /tmp232exclude_slash_tmp = false # Allow /tmp

148| Key | Default | Maturity | Description |148| Key | Default | Maturity | Description |

149| -------------------- | :-------------------: | ------------ | ---------------------------------------------------------------------------------------- |149| -------------------- | :-------------------: | ------------ | ---------------------------------------------------------------------------------------- |

150| `apps` | false | Experimental | Enable ChatGPT Apps/connectors support |150| `apps` | false | Experimental | Enable ChatGPT Apps/connectors support |

151| `apps_mcp_gateway` | false | Experimental | Route Apps MCP calls through `https://api.openai.com/v1/connectors/mcp/` instead of legacy routing |151| `codex_hooks` | false | Under development | Enable lifecycle hooks from `hooks.json`. See [Hooks](https://developers.openai.com/codex/hooks). |

152| `collaboration_modes` | true | Stable | Enable collaboration modes such as plan mode |152| `fast_mode` | true | Stable | Enable Fast mode selection and the `service_tier = "fast"` path |

153| `multi_agent` | true | Stable | Enable subagent collaboration tools |

153| `personality` | true | Stable | Enable personality selection controls |154| `personality` | true | Stable | Enable personality selection controls |

154| `remote_models` | false | Experimental | Refresh remote model list before showing readiness |155| `shell_snapshot` | true | Stable | Snapshot your shell environment to speed up repeated commands |

155| `runtime_metrics` | false | Experimental | Show runtime metrics summaries in TUI turn separators |

156| `request_rule` | true | Stable | Enable Smart approvals (`prefix_rule` suggestions) |

157| `search_tool` | false | Experimental | Enable `search_tool_bm25` so Codex discovers Apps MCP tools via search before tool calls |

158| `shell_snapshot` | false | Beta | Snapshot your shell environment to speed up repeated commands |

159| `shell_tool` | true | Stable | Enable the default `shell` tool |156| `shell_tool` | true | Stable | Enable the default `shell` tool |

160| `use_linux_sandbox_bwrap` | false | Experimental | Use the bubblewrap-based Linux sandbox pipeline |157| `smart_approvals` | false | Experimental | Route eligible approval requests through the guardian reviewer subagent |

161| `unified_exec` | false | Beta | Use the unified PTY-backed exec tool |158| `unified_exec` | `true` except Windows | Stable | Use the unified PTY-backed exec tool |

162| `undo` | true | Stable | Enable undo via per-turn git ghost snapshots |159| `undo` | false | Stable | Enable undo via per-turn git ghost snapshots |

163| `web_search` | true | Deprecated | Legacy toggle; prefer the top-level `web_search` setting |160| `web_search` | true | Deprecated | Legacy toggle; prefer the top-level `web_search` setting |

164| `web_search_cached` | true | Deprecated | Legacy toggle that maps to `web_search = "cached"` when unset |161| `web_search_cached` | false | Deprecated | Legacy toggle that maps to `web_search = "cached"` when unset |

165| `web_search_request` | true | Deprecated | Legacy toggle that maps to `web_search = "live"` when unset |162| `web_search_request` | false | Deprecated | Legacy toggle that maps to `web_search = "live"` when unset |

166 163 

167The Maturity column uses feature maturity labels such as Experimental, Beta,164The Maturity column uses feature maturity labels such as Experimental, Beta,

168 and Stable. See [Feature Maturity](https://developers.openai.com/codex/feature-maturity) for how to165 and Stable. See [Feature Maturity](https://developers.openai.com/codex/feature-maturity) for how to

170 167 

171Omit feature keys to keep their defaults.168Omit feature keys to keep their defaults.

172 169 

170For the current lifecycle hooks MVP, see [Hooks](https://developers.openai.com/codex/hooks).

171 

173### Enabling features172### Enabling features

174 173 

175- In `config.toml`, add `feature_name = true` under `[features]`.174- In `config.toml`, add `feature_name = true` under `[features]`.

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

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| `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. |

20| `analytics.enabled` | `boolean` | Enable or disable analytics for this machine/profile. When unset, the client default applies. |20| `analytics.enabled` | `boolean` | Enable or disable analytics for this machine/profile. When unset, the client default applies. |

21| `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. |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. |

22| `approval_policy.reject.mcp_elicitations` | `boolean` | When `true`, MCP elicitation prompts are auto-rejected instead of shown to the user. |22| `approval_policy.granular.mcp_elicitations` | `boolean` | When `true`, MCP elicitation prompts are allowed to surface instead of being auto-rejected. |

23| `approval_policy.reject.rules` | `boolean` | When `true`, approvals triggered by execpolicy `prompt` rules 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.reject.sandbox_approval` | `boolean` | When `true`, sandbox escalation approval prompts are auto-rejected. |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. |

25| `apps._default.destructive_enabled` | `boolean` | Default allow/deny for app tools with `destructive_hint = true`. |27| `apps._default.destructive_enabled` | `boolean` | Default allow/deny for app tools with `destructive_hint = true`. |

26| `apps._default.enabled` | `boolean` | Default app enabled state for all apps unless overridden per app. |28| `apps._default.enabled` | `boolean` | Default app enabled state for all apps unless overridden per app. |

27| `apps._default.open_world_enabled` | `boolean` | Default allow/deny for app tools with `open_world_hint = true`. |29| `apps._default.open_world_enabled` | `boolean` | Default allow/deny for app tools with `open_world_hint = true`. |

38| `cli_auth_credentials_store` | `file | keyring | auto` | Control where the CLI stores cached credentials (file-based auth.json vs OS keychain). |40| `cli_auth_credentials_store` | `file | keyring | auto` | Control where the CLI stores cached credentials (file-based auth.json vs OS keychain). |

39| `commit_attribution` | `string` | Override the commit co-author trailer text. Set an empty string to disable automatic attribution. |41| `commit_attribution` | `string` | Override the commit co-author trailer text. Set an empty string to disable automatic attribution. |

40| `compact_prompt` | `string` | Inline override for the history compaction prompt. |42| `compact_prompt` | `string` | Inline override for the history compaction prompt. |

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

41| `developer_instructions` | `string` | Additional developer instructions injected into the session (optional). |44| `developer_instructions` | `string` | Additional developer instructions injected into the session (optional). |

42| `disable_paste_burst` | `boolean` | Disable burst-paste detection in the TUI. |45| `disable_paste_burst` | `boolean` | Disable burst-paste detection in the TUI. |

43| `experimental_compact_prompt_file` | `string (path)` | Load the compaction prompt override from a file (experimental). |46| `experimental_compact_prompt_file` | `string (path)` | Load the compaction prompt override from a file (experimental). |

44| `experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`. |47| `experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`. |

45| `features.apps` | `boolean` | Enable ChatGPT Apps/connectors support (experimental). |48| `features.apps` | `boolean` | Enable ChatGPT Apps/connectors support (experimental). |

46| `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). |49| `features.codex_hooks` | `boolean` | Enable lifecycle hooks loaded from `hooks.json` (under development; off by default). |

47| `features.artifact` | `boolean` | Enable native artifact tools such as slides and spreadsheets (under development). |

48| `features.child_agents_md` | `boolean` | Append AGENTS.md scope/precedence guidance even when no AGENTS.md is present (experimental). |

49| `features.collaboration_modes` | `boolean` | Legacy toggle for collaboration modes. Plan and default modes are available in current builds without setting this key. |

50| `features.default_mode_request_user_input` | `boolean` | Allow `request_user_input` in default collaboration mode (under development; off by default). |

51| `features.elevated_windows_sandbox` | `boolean` | Legacy toggle for an earlier elevated Windows sandbox rollout. Current builds do not use it. |

52| `features.enable_request_compression` | `boolean` | Compress streaming request bodies with zstd when supported (stable; on by default). |50| `features.enable_request_compression` | `boolean` | Compress streaming request bodies with zstd when supported (stable; on by default). |

53| `features.experimental_windows_sandbox` | `boolean` | Legacy toggle for an earlier Windows sandbox rollout. Current builds do not use it. |

54| `features.fast_mode` | `boolean` | Enable Fast mode selection and the `service_tier = "fast"` path (stable; on by default). |51| `features.fast_mode` | `boolean` | Enable Fast mode selection and the `service_tier = "fast"` path (stable; on by default). |

55| `features.image_detail_original` | `boolean` | Allow image outputs with `detail = "original"` on supported models (under development). |52| `features.multi_agent` | `boolean` | Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait_agent`, and `close_agent`) (stable; on by default). |

56| `features.image_generation` | `boolean` | Enable the built-in image generation tool (under development). |

57| `features.personality` | `boolean` | Enable personality selection controls (stable; on by default). |53| `features.personality` | `boolean` | Enable personality selection controls (stable; on by default). |

58| `features.powershell_utf8` | `boolean` | Force PowerShell UTF-8 output. Enabled by default on Windows and off elsewhere. |

59| `features.prevent_idle_sleep` | `boolean` | Prevent the machine from sleeping while a turn is actively running (experimental; off by default). |54| `features.prevent_idle_sleep` | `boolean` | Prevent the machine from sleeping while a turn is actively running (experimental; off by default). |

60| `features.remote_models` | `boolean` | Legacy toggle for an older remote-model readiness flow. Current builds do not use it. |

61| `features.request_rule` | `boolean` | Legacy toggle for Smart approvals. Current builds include this behavior by default, so most users can leave this unset. |

62| `features.responses_websockets` | `boolean` | Prefer the Responses API WebSocket transport for supported providers (under development). |

63| `features.responses_websockets_v2` | `boolean` | Enable Responses API WebSocket v2 mode (under development). |

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

65| `features.search_tool` | `boolean` | Legacy toggle for an older Apps discovery flow. Current builds do not use it. |

66| `features.shell_snapshot` | `boolean` | Snapshot shell environment to speed up repeated commands (stable; on by default). |55| `features.shell_snapshot` | `boolean` | Snapshot shell environment to speed up repeated commands (stable; on by default). |

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

68| `features.skill_env_var_dependency_prompt` | `boolean` | Prompt for missing skill environment-variable dependencies (under development). |

69| `features.skill_mcp_dependency_install` | `boolean` | Allow prompting and installing missing MCP dependencies for skills (stable; on by default). |57| `features.skill_mcp_dependency_install` | `boolean` | Allow prompting and installing missing MCP dependencies for skills (stable; on by default). |

70| `features.sqlite` | `boolean` | Enable SQLite-backed state persistence (stable; on by default). |58| `features.smart_approvals` | `boolean` | Route eligible approval requests through the guardian reviewer subagent (experimental; off by default). |

71| `features.steer` | `boolean` | Legacy toggle from an earlier Enter/Tab steering rollout. Current builds always use the current steering behavior. |

72| `features.undo` | `boolean` | Enable undo support (stable; off by default). |59| `features.undo` | `boolean` | Enable undo support (stable; off by default). |

73| `features.unified_exec` | `boolean` | Use the unified PTY-backed exec tool (stable; enabled by default except on Windows). |60| `features.unified_exec` | `boolean` | Use the unified PTY-backed exec tool (stable; enabled by default except on Windows). |

74| `features.use_linux_sandbox_bwrap` | `boolean` | Use the bubblewrap-based Linux sandbox pipeline (experimental; off by default). |

75| `features.web_search` | `boolean` | Deprecated legacy toggle; prefer the top-level `web_search` setting. |61| `features.web_search` | `boolean` | Deprecated legacy toggle; prefer the top-level `web_search` setting. |

76| `features.web_search_cached` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "cached"`. |62| `features.web_search_cached` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "cached"`. |

77| `features.web_search_request` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "live"`. |63| `features.web_search_request` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "live"`. |

105| `mcp_servers.<id>.startup_timeout_sec` | `number` | Override the default 10s startup timeout for an MCP server. |91| `mcp_servers.<id>.startup_timeout_sec` | `number` | Override the default 10s startup timeout for an MCP server. |

106| `mcp_servers.<id>.tool_timeout_sec` | `number` | Override the default 60s per-tool timeout for an MCP server. |92| `mcp_servers.<id>.tool_timeout_sec` | `number` | Override the default 60s per-tool timeout for an MCP server. |

107| `mcp_servers.<id>.url` | `string` | Endpoint for an MCP streamable HTTP server. |93| `mcp_servers.<id>.url` | `string` | Endpoint for an MCP streamable HTTP server. |

108| `model` | `string` | Model to use (e.g., `gpt-5-codex`). |94| `model` | `string` | Model to use (e.g., `gpt-5.4`). |

109| `model_auto_compact_token_limit` | `number` | Token threshold that triggers automatic history compaction (unset uses model defaults). |95| `model_auto_compact_token_limit` | `number` | Token threshold that triggers automatic history compaction (unset uses model defaults). |

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. |96| `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_context_window` | `number` | Context window tokens available to the active model. |97| `model_context_window` | `number` | Context window tokens available to the active model. |

136| `notice.hide_world_writable_warning` | `boolean` | Track acknowledgement of the Windows world-writable directories warning. |122| `notice.hide_world_writable_warning` | `boolean` | Track acknowledgement of the Windows world-writable directories warning. |

137| `notice.model_migrations` | `map<string,string>` | Track acknowledged model migrations as old->new mappings. |123| `notice.model_migrations` | `map<string,string>` | Track acknowledged model migrations as old->new mappings. |

138| `notify` | `array<string>` | Command invoked for notifications; receives a JSON payload from Codex. |124| `notify` | `array<string>` | Command invoked for notifications; receives a JSON payload from Codex. |

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

139| `oss_provider` | `lmstudio | ollama` | Default local provider used when running with `--oss` (defaults to prompting if unset). |126| `oss_provider` | `lmstudio | ollama` | Default local provider used when running with `--oss` (defaults to prompting if unset). |

140| `otel.environment` | `string` | Environment tag applied to emitted OpenTelemetry events (default: `dev`). |127| `otel.environment` | `string` | Environment tag applied to emitted OpenTelemetry events (default: `dev`). |

141| `otel.exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry exporter and provide any endpoint metadata. |128| `otel.exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry exporter and provide any endpoint metadata. |

154| `otel.trace_exporter.<id>.tls.ca-certificate` | `string` | CA certificate path for OTEL trace exporter TLS. |141| `otel.trace_exporter.<id>.tls.ca-certificate` | `string` | CA certificate path for OTEL trace exporter TLS. |

155| `otel.trace_exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL trace exporter TLS. |142| `otel.trace_exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL trace exporter TLS. |

156| `otel.trace_exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL trace exporter TLS. |143| `otel.trace_exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL trace exporter TLS. |

157| `permissions.network.admin_url` | `string` | Admin endpoint for the managed network proxy. |144| `permissions.<name>.filesystem` | `table` | Named filesystem permission profile. Each key is an absolute path or special token such as `:minimal` or `:project_roots`. |

158| `permissions.network.allow_local_binding` | `boolean` | Permit local bind/listen operations through the managed proxy. |145| `permissions.<name>.filesystem.":project_roots".<subpath>` | `"read" | "write" | "none"` | Scoped filesystem access relative to the detected project roots. Use `"."` for the root itself. |

159| `permissions.network.allow_unix_sockets` | `array<string>` | Allowlist of Unix socket paths permitted through the managed proxy. |146| `permissions.<name>.filesystem.<path>` | `"read" | "write" | "none" | table` | Grant direct access for a path or special token, or scope nested entries under that root. |

160| `permissions.network.allow_upstream_proxy` | `boolean` | Allow the managed proxy to chain to another upstream proxy. |147| `permissions.<name>.network.allow_local_binding` | `boolean` | Permit local bind/listen operations through the managed proxy. |

161| `permissions.network.allowed_domains` | `array<string>` | Allowlist of domains permitted through the managed proxy. |148| `permissions.<name>.network.allow_unix_sockets` | `array<string>` | Allowlist of Unix socket paths permitted through the managed proxy. |

162| `permissions.network.dangerously_allow_all_unix_sockets` | `boolean` | Allow the proxy to use arbitrary Unix sockets instead of the default restricted set. |149| `permissions.<name>.network.allow_upstream_proxy` | `boolean` | Allow the managed proxy to chain to another upstream proxy. |

163| `permissions.network.dangerously_allow_non_loopback_admin` | `boolean` | Permit non-loopback bind addresses for the managed proxy admin listener. |150| `permissions.<name>.network.allowed_domains` | `array<string>` | Allowlist of domains permitted through the managed proxy. |

164| `permissions.network.dangerously_allow_non_loopback_proxy` | `boolean` | Permit non-loopback bind addresses for the managed proxy listener. |151| `permissions.<name>.network.dangerously_allow_all_unix_sockets` | `boolean` | Allow the proxy to use arbitrary Unix sockets instead of the default restricted set. |

165| `permissions.network.denied_domains` | `array<string>` | Denylist of domains blocked by the managed proxy. |152| `permissions.<name>.network.dangerously_allow_non_loopback_proxy` | `boolean` | Permit non-loopback bind addresses for the managed proxy listener. |

166| `permissions.network.enable_socks5` | `boolean` | Expose a SOCKS5 listener from the managed network proxy. |153| `permissions.<name>.network.denied_domains` | `array<string>` | Denylist of domains blocked by the managed proxy. |

167| `permissions.network.enable_socks5_udp` | `boolean` | Allow UDP over the SOCKS5 listener when enabled. |154| `permissions.<name>.network.enable_socks5` | `boolean` | Expose a SOCKS5 listener when this permissions profile enables the managed network proxy. |

168| `permissions.network.enabled` | `boolean` | Enable the managed network proxy configuration for subprocesses. |155| `permissions.<name>.network.enable_socks5_udp` | `boolean` | Allow UDP over the SOCKS5 listener when enabled. |

169| `permissions.network.mode` | `limited | full` | Network proxy mode used for subprocess traffic. |156| `permissions.<name>.network.enabled` | `boolean` | Enable network access for this named permissions profile. |

170| `permissions.network.proxy_url` | `string` | HTTP proxy endpoint used by the managed network proxy. |157| `permissions.<name>.network.mode` | `limited | full` | Network proxy mode used for subprocess traffic. |

171| `permissions.network.socks_url` | `string` | SOCKS5 proxy endpoint used by the managed network proxy. |158| `permissions.<name>.network.proxy_url` | `string` | HTTP proxy endpoint used when this permissions profile enables the managed network proxy. |

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

172| `personality` | `none | friendly | pragmatic` | Default communication style for models that advertise `supportsPersonality`; can be overridden per thread/turn or via `/personality`. |160| `personality` | `none | friendly | pragmatic` | Default communication style for models that advertise `supportsPersonality`; can be overridden per thread/turn or via `/personality`. |

173| `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. |161| `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. |

174| `profile` | `string` | Default profile applied at startup (equivalent to `--profile`). |162| `profile` | `string` | Default profile applied at startup (equivalent to `--profile`). |

194| `sandbox_workspace_write.exclude_tmpdir_env_var` | `boolean` | Exclude `$TMPDIR` from writable roots in workspace-write mode. |182| `sandbox_workspace_write.exclude_tmpdir_env_var` | `boolean` | Exclude `$TMPDIR` from writable roots in workspace-write mode. |

195| `sandbox_workspace_write.network_access` | `boolean` | Allow outbound network access inside the workspace-write sandbox. |183| `sandbox_workspace_write.network_access` | `boolean` | Allow outbound network access inside the workspace-write sandbox. |

196| `sandbox_workspace_write.writable_roots` | `array<string>` | Additional writable roots when `sandbox_mode = "workspace-write"`. |184| `sandbox_workspace_write.writable_roots` | `array<string>` | Additional writable roots when `sandbox_mode = "workspace-write"`. |

197| `service_tier` | `flex | fast` | Preferred service tier for new turns. `fast` is honored only when the `features.fast_mode` gate is enabled. |185| `service_tier` | `flex | fast` | Preferred service tier for new turns. |

198| `shell_environment_policy.exclude` | `array<string>` | Glob patterns for removing environment variables after the defaults. |186| `shell_environment_policy.exclude` | `array<string>` | Glob patterns for removing environment variables after the defaults. |

199| `shell_environment_policy.experimental_use_profile` | `boolean` | Use the user shell profile when spawning subprocesses. |187| `shell_environment_policy.experimental_use_profile` | `boolean` | Use the user shell profile when spawning subprocesses. |

200| `shell_environment_policy.ignore_default_excludes` | `boolean` | Keep variables containing KEY/SECRET/TOKEN before other filters run. |188| `shell_environment_policy.ignore_default_excludes` | `boolean` | Keep variables containing KEY/SECRET/TOKEN before other filters run. |

209| `suppress_unstable_features_warning` | `boolean` | Suppress the warning that appears when under-development feature flags are enabled. |197| `suppress_unstable_features_warning` | `boolean` | Suppress the warning that appears when under-development feature flags are enabled. |

210| `tool_output_token_limit` | `number` | Token budget for storing individual tool/function outputs in history. |198| `tool_output_token_limit` | `number` | Token budget for storing individual tool/function outputs in history. |

211| `tools.view_image` | `boolean` | Enable the local-image attachment tool `view_image`. |199| `tools.view_image` | `boolean` | Enable the local-image attachment tool `view_image`. |

212| `tools.web_search` | `boolean` | Deprecated legacy toggle for web search; prefer the top-level `web_search` setting. |200| `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. |

213| `tui` | `table` | TUI-specific options such as enabling inline desktop notifications. |201| `tui` | `table` | TUI-specific options such as enabling inline desktop notifications. |

214| `tui.alternate_screen` | `auto | always | never` | Control alternate screen usage for the TUI (default: auto; auto skips it in Zellij to preserve scrollback). |202| `tui.alternate_screen` | `auto | always | never` | Control alternate screen usage for the TUI (default: auto; auto skips it in Zellij to preserve scrollback). |

215| `tui.animations` | `boolean` | Enable terminal animations (welcome screen, shimmer, spinner) (default: true). |203| `tui.animations` | `boolean` | Enable terminal animations (welcome screen, shimmer, spinner) (default: true). |

222| `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. |210| `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. |

223| `windows_wsl_setup_acknowledged` | `boolean` | Track Windows onboarding acknowledgement (Windows only). |211| `windows_wsl_setup_acknowledged` | `boolean` | Track Windows onboarding acknowledgement (Windows only). |

224| `windows.sandbox` | `unelevated | elevated` | Windows-only native sandbox mode when running Codex natively on Windows. |212| `windows.sandbox` | `unelevated | elevated` | Windows-only native sandbox mode when running Codex natively on Windows. |

213| `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. |

225 214 

226Key215Key

227 216 

325 314 

326Type / Values315Type / Values

327 316 

328`untrusted | on-request | never | { reject = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool } }`317`untrusted | on-request | never | { granular = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool, request_permissions = bool, skill_approval = bool } }`

329 318 

330Details319Details

331 320 

332Controls 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.321Controls 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.

333 322 

334Key323Key

335 324 

336`approval_policy.reject.mcp_elicitations`325`approval_policy.granular.mcp_elicitations`

337 326 

338Type / Values327Type / Values

339 328 

341 330 

342Details331Details

343 332 

344When `true`, MCP elicitation prompts are auto-rejected instead of shown to the user.333When `true`, MCP elicitation prompts are allowed to surface instead of being auto-rejected.

345 334 

346Key335Key

347 336 

348`approval_policy.reject.rules`337`approval_policy.granular.request_permissions`

349 338 

350Type / Values339Type / Values

351 340 

353 342 

354Details343Details

355 344 

356When `true`, approvals triggered by execpolicy `prompt` rules are auto-rejected.345When `true`, prompts from the `request_permissions` tool are allowed to surface.

357 346 

358Key347Key

359 348 

360`approval_policy.reject.sandbox_approval`349`approval_policy.granular.rules`

361 350 

362Type / Values351Type / Values

363 352 

365 354 

366Details355Details

367 356 

368When `true`, sandbox escalation approval prompts are auto-rejected.357When `true`, approvals triggered by execpolicy `prompt` rules are allowed to surface.

358 

359Key

360 

361`approval_policy.granular.sandbox_approval`

362 

363Type / Values

364 

365`boolean`

366 

367Details

368 

369When `true`, sandbox escalation approval prompts are allowed to surface.

370 

371Key

372 

373`approval_policy.granular.skill_approval`

374 

375Type / Values

376 

377`boolean`

378 

379Details

380 

381When `true`, skill-script approval prompts are allowed to surface.

369 382 

370Key383Key

371 384 

561 574 

562Key575Key

563 576 

577`default_permissions`

578 

579Type / Values

580 

581`string`

582 

583Details

584 

585Name of the default permissions profile to apply to sandboxed tool calls.

586 

587Key

588 

564`developer_instructions`589`developer_instructions`

565 590 

566Type / Values591Type / Values

621 646 

622Key647Key

623 648 

624`features.apps_mcp_gateway`649`features.codex_hooks`

625 

626Type / Values

627 

628`boolean`

629 

630Details

631 

632Route Apps MCP calls through the OpenAI connectors MCP gateway (`https://api.openai.com/v1/connectors/mcp/`) instead of legacy routing (experimental).

633 

634Key

635 

636`features.artifact`

637 650 

638Type / Values651Type / Values

639 652 

641 654 

642Details655Details

643 656 

644Enable native artifact tools such as slides and spreadsheets (under development).657Enable lifecycle hooks loaded from `hooks.json` (under development; off by default).

645 

646Key

647 

648`features.child_agents_md`

649 

650Type / Values

651 

652`boolean`

653 

654Details

655 

656Append AGENTS.md scope/precedence guidance even when no AGENTS.md is present (experimental).

657 

658Key

659 

660`features.collaboration_modes`

661 

662Type / Values

663 

664`boolean`

665 

666Details

667 

668Legacy toggle for collaboration modes. Plan and default modes are available in current builds without setting this key.

669 

670Key

671 

672`features.default_mode_request_user_input`

673 

674Type / Values

675 

676`boolean`

677 

678Details

679 

680Allow `request_user_input` in default collaboration mode (under development; off by default).

681 

682Key

683 

684`features.elevated_windows_sandbox`

685 

686Type / Values

687 

688`boolean`

689 

690Details

691 

692Legacy toggle for an earlier elevated Windows sandbox rollout. Current builds do not use it.

693 658 

694Key659Key

695 660 

705 670 

706Key671Key

707 672 

708`features.experimental_windows_sandbox`

709 

710Type / Values

711 

712`boolean`

713 

714Details

715 

716Legacy toggle for an earlier Windows sandbox rollout. Current builds do not use it.

717 

718Key

719 

720`features.fast_mode`673`features.fast_mode`

721 674 

722Type / Values675Type / Values

729 682 

730Key683Key

731 684 

732`features.image_detail_original`685`features.multi_agent`

733 686 

734Type / Values687Type / Values

735 688 

737 690 

738Details691Details

739 692 

740Allow image outputs with `detail = "original"` on supported models (under development).693Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait_agent`, and `close_agent`) (stable; on by default).

741 

742Key

743 

744`features.image_generation`

745 

746Type / Values

747 

748`boolean`

749 

750Details

751 

752Enable the built-in image generation tool (under development).

753 694 

754Key695Key

755 696 

765 706 

766Key707Key

767 708 

768`features.powershell_utf8`

769 

770Type / Values

771 

772`boolean`

773 

774Details

775 

776Force PowerShell UTF-8 output. Enabled by default on Windows and off elsewhere.

777 

778Key

779 

780`features.prevent_idle_sleep`709`features.prevent_idle_sleep`

781 710 

782Type / Values711Type / Values

789 718 

790Key719Key

791 720 

792`features.remote_models`

793 

794Type / Values

795 

796`boolean`

797 

798Details

799 

800Legacy toggle for an older remote-model readiness flow. Current builds do not use it.

801 

802Key

803 

804`features.request_rule`

805 

806Type / Values

807 

808`boolean`

809 

810Details

811 

812Legacy toggle for Smart approvals. Current builds include this behavior by default, so most users can leave this unset.

813 

814Key

815 

816`features.responses_websockets`

817 

818Type / Values

819 

820`boolean`

821 

822Details

823 

824Prefer the Responses API WebSocket transport for supported providers (under development).

825 

826Key

827 

828`features.responses_websockets_v2`

829 

830Type / Values

831 

832`boolean`

833 

834Details

835 

836Enable Responses API WebSocket v2 mode (under development).

837 

838Key

839 

840`features.runtime_metrics`

841 

842Type / Values

843 

844`boolean`

845 

846Details

847 

848Show runtime metrics summary in TUI turn separators (experimental).

849 

850Key

851 

852`features.search_tool`

853 

854Type / Values

855 

856`boolean`

857 

858Details

859 

860Legacy toggle for an older Apps discovery flow. Current builds do not use it.

861 

862Key

863 

864`features.shell_snapshot`721`features.shell_snapshot`

865 722 

866Type / Values723Type / Values

885 742 

886Key743Key

887 744 

888`features.skill_env_var_dependency_prompt`

889 

890Type / Values

891 

892`boolean`

893 

894Details

895 

896Prompt for missing skill environment-variable dependencies (under development).

897 

898Key

899 

900`features.skill_mcp_dependency_install`745`features.skill_mcp_dependency_install`

901 746 

902Type / Values747Type / Values

909 754 

910Key755Key

911 756 

912`features.sqlite`757`features.smart_approvals`

913 

914Type / Values

915 

916`boolean`

917 

918Details

919 

920Enable SQLite-backed state persistence (stable; on by default).

921 

922Key

923 

924`features.steer`

925 758 

926Type / Values759Type / Values

927 760 

929 762 

930Details763Details

931 764 

932Legacy toggle from an earlier Enter/Tab steering rollout. Current builds always use the current steering behavior.765Route eligible approval requests through the guardian reviewer subagent (experimental; off by default).

933 766 

934Key767Key

935 768 

957 790 

958Key791Key

959 792 

960`features.use_linux_sandbox_bwrap`

961 

962Type / Values

963 

964`boolean`

965 

966Details

967 

968Use the bubblewrap-based Linux sandbox pipeline (experimental; off by default).

969 

970Key

971 

972`features.web_search`793`features.web_search`

973 794 

974Type / Values795Type / Values

1373 1194 

1374Details1195Details

1375 1196 

1376Model to use (e.g., `gpt-5-codex`).1197Model to use (e.g., `gpt-5.4`).

1377 1198 

1378Key1199Key

1379 1200 

1737 1558 

1738Key1559Key

1739 1560 

1561`openai_base_url`

1562 

1563Type / Values

1564 

1565`string`

1566 

1567Details

1568 

1569Base URL override for the built-in `openai` model provider.

1570 

1571Key

1572 

1740`oss_provider`1573`oss_provider`

1741 1574 

1742Type / Values1575Type / Values

1953 1786 

1954Key1787Key

1955 1788 

1956`permissions.network.admin_url`1789`permissions.<name>.filesystem`

1957 1790 

1958Type / Values1791Type / Values

1959 1792 

1960`string`1793`table`

1961 1794 

1962Details1795Details

1963 1796 

1964Admin endpoint for the managed network proxy.1797Named filesystem permission profile. Each key is an absolute path or special token such as `:minimal` or `:project_roots`.

1965 1798 

1966Key1799Key

1967 1800 

1968`permissions.network.allow_local_binding`1801`permissions.<name>.filesystem.":project_roots".<subpath>`

1969 1802 

1970Type / Values1803Type / Values

1971 1804 

1972`boolean`1805`"read" | "write" | "none"`

1973 1806 

1974Details1807Details

1975 1808 

1976Permit local bind/listen operations through the managed proxy.1809Scoped filesystem access relative to the detected project roots. Use `"."` for the root itself.

1977 1810 

1978Key1811Key

1979 1812 

1980`permissions.network.allow_unix_sockets`1813`permissions.<name>.filesystem.<path>`

1981 1814 

1982Type / Values1815Type / Values

1983 1816 

1984`array<string>`1817`"read" | "write" | "none" | table`

1985 1818 

1986Details1819Details

1987 1820 

1988Allowlist of Unix socket paths permitted through the managed proxy.1821Grant direct access for a path or special token, or scope nested entries under that root.

1989 1822 

1990Key1823Key

1991 1824 

1992`permissions.network.allow_upstream_proxy`1825`permissions.<name>.network.allow_local_binding`

1993 1826 

1994Type / Values1827Type / Values

1995 1828 

1997 1830 

1998Details1831Details

1999 1832 

2000Allow the managed proxy to chain to another upstream proxy.1833Permit local bind/listen operations through the managed proxy.

2001 1834 

2002Key1835Key

2003 1836 

2004`permissions.network.allowed_domains`1837`permissions.<name>.network.allow_unix_sockets`

2005 1838 

2006Type / Values1839Type / Values

2007 1840 

2009 1842 

2010Details1843Details

2011 1844 

2012Allowlist of domains permitted through the managed proxy.1845Allowlist of Unix socket paths permitted through the managed proxy.

2013 1846 

2014Key1847Key

2015 1848 

2016`permissions.network.dangerously_allow_all_unix_sockets`1849`permissions.<name>.network.allow_upstream_proxy`

2017 1850 

2018Type / Values1851Type / Values

2019 1852 

2021 1854 

2022Details1855Details

2023 1856 

2024Allow the proxy to use arbitrary Unix sockets instead of the default restricted set.1857Allow the managed proxy to chain to another upstream proxy.

1858 

1859Key

1860 

1861`permissions.<name>.network.allowed_domains`

1862 

1863Type / Values

1864 

1865`array<string>`

1866 

1867Details

1868 

1869Allowlist of domains permitted through the managed proxy.

2025 1870 

2026Key1871Key

2027 1872 

2028`permissions.network.dangerously_allow_non_loopback_admin`1873`permissions.<name>.network.dangerously_allow_all_unix_sockets`

2029 1874 

2030Type / Values1875Type / Values

2031 1876 

2033 1878 

2034Details1879Details

2035 1880 

2036Permit non-loopback bind addresses for the managed proxy admin listener.1881Allow the proxy to use arbitrary Unix sockets instead of the default restricted set.

2037 1882 

2038Key1883Key

2039 1884 

2040`permissions.network.dangerously_allow_non_loopback_proxy`1885`permissions.<name>.network.dangerously_allow_non_loopback_proxy`

2041 1886 

2042Type / Values1887Type / Values

2043 1888 

2049 1894 

2050Key1895Key

2051 1896 

2052`permissions.network.denied_domains`1897`permissions.<name>.network.denied_domains`

2053 1898 

2054Type / Values1899Type / Values

2055 1900 

2061 1906 

2062Key1907Key

2063 1908 

2064`permissions.network.enable_socks5`1909`permissions.<name>.network.enable_socks5`

2065 1910 

2066Type / Values1911Type / Values

2067 1912 

2069 1914 

2070Details1915Details

2071 1916 

2072Expose a SOCKS5 listener from the managed network proxy.1917Expose a SOCKS5 listener when this permissions profile enables the managed network proxy.

2073 1918 

2074Key1919Key

2075 1920 

2076`permissions.network.enable_socks5_udp`1921`permissions.<name>.network.enable_socks5_udp`

2077 1922 

2078Type / Values1923Type / Values

2079 1924