OpenAI - Codex Docs Changes

agent-approvals-security.md +253 −0 added

Details

1# Agent approvals & security

3Codex helps protect your code and data and reduces the risk of misuse.

5This page covers how to operate Codex safely, including sandboxing, approvals,

6 and network access. If you are looking for Codex Security, the product for

7 scanning connected GitHub repositories, see [Codex Security](https://developers.openai.com/codex/security).

9By default, the agent runs with network access turned off. Locally, Codex uses an OS-enforced sandbox that limits what it can touch (typically to the current workspace), plus an approval policy that controls when it must stop and ask you before acting.

11For a high-level explanation of how sandboxing works across the Codex app, IDE

12extension, and CLI, see [Sandboxing](https://developers.openai.com/codex/concepts/sandboxing).

14## Sandbox and approvals

16Codex security controls come from two layers that work together:

18- **Sandbox mode**: What Codex can do technically (for example, where it can write and whether it can reach the network) when it executes model-generated commands.

19- **Approval policy**: When Codex must ask you before it executes an action (for example, leaving the sandbox, using the network, or running commands outside a trusted set).

21Codex uses different sandbox modes depending on where you run it:

23- **Codex cloud**: Runs in isolated OpenAI-managed containers, preventing access to your host system or unrelated data. Uses a two-phase runtime model: setup runs before the agent phase and can access the network to install specified dependencies, then the agent phase runs offline by default unless you enable internet access for that environment. Secrets configured for cloud environments are available only during setup and are removed before the agent phase starts.

24- **Codex CLI / IDE extension**: OS-level mechanisms enforce sandbox policies. Defaults include no network access and write permissions limited to the active workspace. You can configure the sandbox, approval policy, and network settings based on your risk tolerance.

26In the `Auto` preset (for example, `--full-auto`), Codex can read files, make edits, and run commands in the working directory automatically.

28Codex asks for approval to edit files outside the workspace or to run commands that require network access. If you want to chat or plan without making changes, switch to `read-only` mode with the `/permissions` command.

30Codex can also elicit approval for app (connector) tool calls that advertise side effects, even when the action isn't a shell command or file change. Destructive app/MCP tool calls always require approval when the tool advertises a destructive annotation, even if it also advertises other hints (for example, read-only hints).

32## Network access [Elevated Risk](https://help.openai.com/articles/20001061)

34For Codex cloud, see [agent internet access](https://developers.openai.com/codex/cloud/internet-access) to enable full internet access or a domain allow list.

36For the Codex app, CLI, or IDE Extension, the default `workspace-write` sandbox mode keeps network access turned off unless you enable it in your configuration:

38```toml

39[sandbox_workspace_write]

40network_access = true

41```

43You can also control the [web search tool](https://platform.openai.com/docs/guides/tools-web-search) without granting full network access to spawned commands. Codex defaults to using a web search cache to access results. The cache is an OpenAI-maintained index of web results, so cached mode returns pre-indexed results instead of fetching live pages. This reduces exposure to prompt injection from arbitrary live content, but you should still treat web results as untrusted. If you are using `--yolo` or another [full access sandbox setting](#common-sandbox-and-approval-combinations), web search defaults to live results. Use `--search` or set `web_search = "live"` to allow live browsing, or set it to `"disabled"` to turn the tool off:

45```toml

46web_search = "cached" # default

47# web_search = "disabled"

48# web_search = "live" # same as --search

49```

51Use caution when enabling network access or web search in Codex. Prompt injection can cause the agent to fetch and follow untrusted instructions.

53## Defaults and recommendations

55- On launch, Codex detects whether the folder is version-controlled and recommends:

56 - Version-controlled folders: `Auto` (workspace write + on-request approvals)

57 - Non-version-controlled folders: `read-only`

58- Depending on your setup, Codex may also start in `read-only` until you explicitly trust the working directory (for example, via an onboarding prompt or `/permissions`).

59- The workspace includes the current directory and temporary directories like `/tmp`. Use the `/status` command to see which directories are in the workspace.

60- To accept the defaults, run `codex`.

61- You can set these explicitly:

62 - `codex --sandbox workspace-write --ask-for-approval on-request`

63 - `codex --sandbox read-only --ask-for-approval on-request`

65### Protected paths in writable roots

67In the default `workspace-write` sandbox policy, writable roots still include protected paths:

69- `<writable_root>/.git` is protected as read-only whether it appears as a directory or file.

70- If `<writable_root>/.git` is a pointer file (`gitdir: ...`), the resolved Git directory path is also protected as read-only.

71- `<writable_root>/.agents` is protected as read-only when it exists as a directory.

72- `<writable_root>/.codex` is protected as read-only when it exists as a directory.

73- Protection is recursive, so everything under those paths is read-only.

75### Run without approval prompts

77You can disable approval prompts with `--ask-for-approval never` or `-a never` (shorthand).

79This option works with all `--sandbox` modes, so you still control Codex's level of autonomy. Codex makes a best effort within the constraints you set.

81If 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.

83For 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.

85### Common sandbox and approval combinations

87| Intent | Flags | Effect |

88| ----------------------------------------------------------------- | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------ |

89| Auto (preset) | *no flags needed* or `--full-auto` | Codex can read files, make edits, and run commands in the workspace. Codex requires approval to edit outside the workspace or to access network. |

90| Safe read-only browsing | `--sandbox read-only --ask-for-approval on-request` | Codex can read files and answer questions. Codex requires approval to make edits, run commands, or access network. |

91| Read-only non-interactive (CI) | `--sandbox read-only --ask-for-approval never` | Codex can only read files; never asks for approval. |

92| Automatically edit but ask for approval to run untrusted commands | `--sandbox workspace-write --ask-for-approval untrusted` | Codex can read and edit files but asks for approval before running untrusted commands. |

93| Dangerous full access | `--dangerously-bypass-approvals-and-sandbox` (alias: `--yolo`) | [Elevated Risk](https://help.openai.com/articles/20001061) No sandbox; no approvals *(not recommended)* |

95`--full-auto` is a convenience alias for `--sandbox workspace-write --ask-for-approval on-request`.

97With `--ask-for-approval untrusted`, Codex runs only known-safe read operations automatically. Commands that can mutate state or trigger external execution paths (for example, destructive Git operations or Git output/config-override flags) require approval.

99#### Configuration in `config.toml`

100

101For the broader configuration workflow, see [Config basics](https://developers.openai.com/codex/config-basic), [Advanced Config](https://developers.openai.com/codex/config-advanced#approval-policies-and-sandbox-modes), and the [Configuration Reference](https://developers.openai.com/codex/config-reference).

102

103```toml

104# Always ask for approval mode

105approval_policy = "untrusted"

106sandbox_mode = "read-only"

107allow_login_shell = false # optional hardening: disallow login shells for shell-based tools

108

109# Optional: Allow network in workspace-write mode

110[sandbox_workspace_write]

111network_access = true

112

113# Optional: granular approval prompt auto-rejection

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

115```

116

117You can also save presets as profiles, then select them with `codex --profile <name>`:

118

119```toml

120[profiles.full_auto]

121approval_policy = "on-request"

122sandbox_mode = "workspace-write"

123

124[profiles.readonly_quiet]

125approval_policy = "never"

126sandbox_mode = "read-only"

127```

128

129### Test the sandbox locally

130

131To see what happens when a command runs under the Codex sandbox, use these Codex CLI commands:

132

133```bash

134# macOS

135codex sandbox macos [--full-auto] [--log-denials] [COMMAND]...

136# Linux

137codex sandbox linux [--full-auto] [COMMAND]...

138```

139

140The `sandbox` command is also available as `codex debug`, and the platform helpers have aliases (for example `codex sandbox seatbelt` and `codex sandbox landlock`).

141

142## OS-level sandbox

143

144Codex enforces the sandbox differently depending on your OS:

145

146- **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.

147- **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.

148- **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.

149

150If 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:

151

152```json

153{

154 "chatgpt.runCodexInWindowsSubsystemForLinux": true

155}

156```

157

158This ensures the IDE extension inherits Linux sandbox semantics for commands, approvals, and filesystem access even when the host OS is Windows. Learn more in the [Windows setup guide](https://developers.openai.com/codex/windows).

159

160When running natively on Windows, configure the native sandbox mode in `config.toml`:

161

162```toml

163[windows]

164sandbox = "unelevated" # or "elevated"

165```

166

167See the [Windows setup guide](https://developers.openai.com/codex/windows#windows-sandbox) for details.

168

169When you run Linux in a containerized environment such as Docker, the sandbox may not work if the host or container configuration doesn’t support the required `Landlock` and `seccomp` features.

170

171In that case, configure your Docker container to provide the isolation you need, then run `codex` with `--sandbox danger-full-access` (or the `--dangerously-bypass-approvals-and-sandbox` flag) inside the container.

172

173## Version control

174

175Codex works best with a version control workflow:

176

177- Work on a feature branch and keep `git status` clean before delegating. This keeps Codex patches easier to isolate and revert.

178- Prefer patch-based workflows (for example, `git diff`/`git apply`) over editing tracked files directly. Commit frequently so you can roll back in small increments.

179- Treat Codex suggestions like any other PR: run targeted verification, review diffs, and document decisions in commit messages for auditing.

180

181## Monitoring and telemetry

182

183Codex supports opt-in monitoring via OpenTelemetry (OTel) to help teams audit usage, investigate issues, and meet compliance requirements without weakening local security defaults. Telemetry is off by default; enable it explicitly in your configuration.

184

185### Overview

186

187- Codex turns off OTel export by default to keep local runs self-contained.

188- When enabled, Codex emits structured log events covering conversations, API requests, SSE/WebSocket stream activity, user prompts (redacted by default), tool approval decisions, and tool results.

189- Codex tags exported events with `service.name` (originator), CLI version, and an environment label to separate dev/staging/prod traffic.

190

191### Enable OTel (opt-in)

192

193Add an `[otel]` block to your Codex configuration (typically `~/.codex/config.toml`), choosing an exporter and whether to log prompt text.

194

195```toml

196[otel]

197environment = "staging" # dev | staging | prod

198exporter = "none" # none | otlp-http | otlp-grpc

199log_user_prompt = false # redact prompt text unless policy allows

200```

201

202- `exporter = "none"` leaves instrumentation active but doesn't send data anywhere.

203- To send events to your own collector, pick one of:

204

205```toml

206[otel]

207exporter = { otlp-http = {

208 endpoint = "https://otel.example.com/v1/logs",

209 protocol = "binary",

210 headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" }

211}}

212```

213

214```toml

215[otel]

216exporter = { otlp-grpc = {

217 endpoint = "https://otel.example.com:4317",

218 headers = { "x-otlp-meta" = "abc123" }

219}}

220```

221

222Codex batches events and flushes them on shutdown. Codex exports only telemetry produced by its OTel module.

223

224### Event categories

225

226Representative event types include:

227

228- `codex.conversation_starts` (model, reasoning settings, sandbox/approval policy)

229- `codex.api_request` (attempt, status/success, duration, and error details)

230- `codex.sse_event` (stream event kind, success/failure, duration, plus token counts on `response.completed`)

231- `codex.websocket_request` and `codex.websocket_event` (request duration plus per-message kind/success/error)

232- `codex.user_prompt` (length; content redacted unless explicitly enabled)

233- `codex.tool_decision` (approved/denied, source: configuration vs. user)

234- `codex.tool_result` (duration, success, output snippet)

235

236Associated OTel metrics (counter plus duration histogram pairs) include `codex.api_request`, `codex.sse_event`, `codex.websocket.request`, `codex.websocket.event`, and `codex.tool.call` (with corresponding `.duration_ms` instruments).

237

238For the full event catalog and configuration reference, see the [Codex configuration documentation on GitHub](https://github.com/openai/codex/blob/main/docs/config.md#otel).

239

240### Security and privacy guidance

241

242- Keep `log_user_prompt = false` unless policy explicitly permits storing prompt contents. Prompts can include source code and sensitive data.

243- Route telemetry only to collectors you control; apply retention limits and access controls aligned with your compliance requirements.

244- Treat tool arguments and outputs as sensitive. Favor redaction at the collector or SIEM when possible.

245- Review local data retention settings (for example, `history.persistence` / `history.max_bytes`) if you don't want Codex to save session transcripts under `CODEX_HOME`. See [Advanced Config](https://developers.openai.com/codex/config-advanced#history-persistence) and [Configuration Reference](https://developers.openai.com/codex/config-reference).

246- If you run the CLI with network access turned off, OTel export can't reach your collector. To export, allow network access in `workspace-write` mode for the OTel endpoint, or export from Codex cloud with the collector domain on your approved list.

247- Review events periodically for approval/sandbox changes and unexpected tool executions.

248

249OTel is optional and designed to complement, not replace, the sandbox and approval protections described above.

250

251## Managed configuration

252

253Enterprise admins can configure Codex security settings for their workspace in [Managed configuration](https://developers.openai.com/codex/enterprise/managed-configuration). See that page for setup and policy details.

ambassadors.md +2 −0

Details

10 10

11[Apply Today](https://openai.com/form/codex-ambassadors)11[Apply Today](https://openai.com/form/codex-ambassadors)

12 12

13[Upcoming Meetups](https://developers.openai.com/codex/community/meetups)

13![Codex Ambassadors leading a community workshop](/images/codex/ambassadors/ambassadors-18.jpg) ![Builders collaborating during a Codex Ambassador event](/images/codex/ambassadors/ambassadors-25.jpg)15![Codex Ambassadors leading a community workshop](/images/codex/ambassadors/ambassadors-18.jpg) ![Builders collaborating during a Codex Ambassador event](/images/codex/ambassadors/ambassadors-25.jpg)

14 16

15Ambassadors run hands-on meetups, workshops, and community sessions17Ambassadors run hands-on meetups, workshops, and community sessions

app.md +4 −2

Details

4 4

5ChatGPT Plus, Pro, Business, Edu, and Enterprise plans include Codex. Learn more about [what's included](https://developers.openai.com/codex/pricing).5ChatGPT Plus, Pro, Business, Edu, and Enterprise plans include Codex. Learn more about [what's included](https://developers.openai.com/codex/pricing).

6 6

7![Codex app for Windows showing a project sidebar, active thread, and review pane](/images/codex/windows/codex-windows-light.webp)

7![Codex app window with a project sidebar, active thread, and review pane](/images/codex/app/app-screenshot-light.webp)9![Codex app window with a project sidebar, active thread, and review pane](/images/codex/app/app-screenshot-light.webp)

8 10

9## Getting started11## Getting started

12 14

131. Download and install the Codex app151. Download and install the Codex app

14 16

~~15 The Codex app is currently only available for macOS.~~17 Download the Codex app for Windows or macOS.

16 18

17 [Download for macOS](https://persistent.oaistatic.com/codex-app-prod/Codex.dmg)19 [Download for macOS](https://persistent.oaistatic.com/codex-app-prod/Codex.dmg)

18 20

~~19 [Get notified for Windows and Linux](https://openai.com/form/codex-app/)~~21 [Get notified for Linux](https://openai.com/form/codex-app/)

202. Open Codex and sign in222. Open Codex and sign in

21 23

22 Once you downloaded and installed the Codex app, open it and sign in with your ChatGPT account or an OpenAI API key.24 Once you downloaded and installed the Codex app, open it and sign in with your ChatGPT account or an OpenAI API key.

app-server.md +282 −27

Details

116- **Start (or resume) a thread**: Call `thread/start` for a new conversation, `thread/resume` to continue an existing one, or `thread/fork` to branch history into a new thread id.116- **Start (or resume) a thread**: Call `thread/start` for a new conversation, `thread/resume` to continue an existing one, or `thread/fork` to branch history into a new thread id.

117- **Begin a turn**: Call `turn/start` with the target `threadId` and user input. Optional fields override model, personality, `cwd`, sandbox policy, and more.117- **Begin a turn**: Call `turn/start` with the target `threadId` and user input. Optional fields override model, personality, `cwd`, sandbox policy, and more.

118- **Steer an active turn**: Call `turn/steer` to append user input to the currently in-flight turn without creating a new turn.118- **Steer an active turn**: Call `turn/steer` to append user input to the currently in-flight turn without creating a new turn.

119- **Stream events**: After `turn/start`, keep reading notifications on stdout: `item/started`, `item/completed`, `item/agentMessage/delta`, tool progress, and other updates.119- **Stream events**: After `turn/start`, keep reading notifications on stdout: `thread/archived`, `thread/unarchived`, `item/started`, `item/completed`, `item/agentMessage/delta`, tool progress, and other updates.

120- **Finish the turn**: The server emits `turn/completed` with final status when the model finishes or after a `turn/interrupt` cancellation.120- **Finish the turn**: The server emits `turn/completed` with final status when the model finishes or after a `turn/interrupt` cancellation.

121 121

122## Initialization122## Initialization

201- `thread/start` - create a new thread; emits `thread/started` and automatically subscribes you to turn/item events for that thread.201- `thread/start` - create a new thread; emits `thread/started` and automatically subscribes you to turn/item events for that thread.

202- `thread/resume` - reopen an existing thread by id so later `turn/start` calls append to it.202- `thread/resume` - reopen an existing thread by id so later `turn/start` calls append to it.

203- `thread/fork` - fork a thread into a new thread id by copying stored history; emits `thread/started` for the new thread.203- `thread/fork` - fork a thread into a new thread id by copying stored history; emits `thread/started` for the new thread.

204- `thread/read` - read a stored thread by id without resuming it; set `includeTurns` to return full turn history.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`.

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

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

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

208- `thread/unarchive` - restore an archived thread rollout back into the active sessions directory; returns the restored `thread`.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`.

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

210- `thread/status/changed` - notification emitted when a loaded thread's runtime `status` changes.

209- `thread/compact/start` - trigger conversation history compaction for a thread; returns `{}` immediately while progress streams via `turn/*` and `item/*` notifications.211- `thread/compact/start` - trigger conversation history compaction for a thread; returns `{}` immediately while progress streams via `turn/*` and `item/*` notifications.

210- `thread/rollback` - drop the last N turns from the in-memory context and persist a rollback marker; returns the updated `thread`.212- `thread/rollback` - drop the last N turns from the in-memory context and persist a rollback marker; returns the updated `thread`.

211- `turn/start` - add user input to a thread and begin Codex generation; responds with the initial `turn` and streams events. For `collaborationMode`, `settings.developer_instructions: null` means "use built-in instructions for the selected mode."213- `turn/start` - add user input to a thread and begin Codex generation; responds with the initial `turn` and streams events. For `collaborationMode`, `settings.developer_instructions: null` means "use built-in instructions for the selected mode."

223- `tool/requestUserInput` - prompt the user with 1-3 short questions for a tool call (experimental); questions can set `isOther` for a free-form option.225- `tool/requestUserInput` - prompt the user with 1-3 short questions for a tool call (experimental); questions can set `isOther` for a free-form option.

224- `config/mcpServer/reload` - reload MCP server configuration from disk and queue a refresh for loaded threads.226- `config/mcpServer/reload` - reload MCP server configuration from disk and queue a refresh for loaded threads.

225- `mcpServerStatus/list` - list MCP servers, tools, resources, and auth status (cursor + limit pagination).227- `mcpServerStatus/list` - list MCP servers, tools, resources, and auth status (cursor + limit pagination).

226- `feedback/upload` - submit a feedback report (classification + optional reason/logs + conversation id).228- `windowsSandbox/setupStart` - start Windows sandbox setup for `elevated` or `unelevated` mode; returns quickly and later emits `windowsSandbox/setupCompleted`.

229- `feedback/upload` - submit a feedback report (classification + optional reason/logs + conversation id, plus optional `extraLogFiles` attachments).

227- `config/read` - fetch the effective configuration on disk after resolving configuration layering.230- `config/read` - fetch the effective configuration on disk after resolving configuration layering.

231- `externalAgentConfig/detect` - detect migratable external-agent artifacts with `includeHome` and optional `cwds`; each detected item includes `cwd` (`null` for home).

232- `externalAgentConfig/import` - apply selected external-agent migration items by passing explicit `migrationItems` with `cwd` (`null` for home).

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

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

230- `configRequirements/read` - fetch requirements from `requirements.toml` and/or MDM, including allow-lists and residency requirements (or `null` if you haven’t set any up).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).

231 236

232## Models237## Models

233 238

239{ "method": "model/list", "id": 6, "params": { "limit": 20, "includeHidden": false } }244{ "method": "model/list", "id": 6, "params": { "limit": 20, "includeHidden": false } }

240{ "id": 6, "result": {245{ "id": 6, "result": {

241 "data": [{246 "data": [{

242 "id": "gpt-5.2-codex",247 "id": "gpt-5.4",

243 "model": "gpt-5.2-codex",248 "model": "gpt-5.4",

244 "upgrade": "gpt-5.3-codex",249 "displayName": "GPT-5.4",

245 "displayName": "GPT-5.2 Codex",

246 "hidden": false,250 "hidden": false,

247 "defaultReasoningEffort": "medium",251 "defaultReasoningEffort": "medium",

248 "reasoningEffort": [{252 "supportedReasoningEfforts": [{

249 "effort": "low",253 "reasoningEffort": "low",

250 "description": "Lower latency"254 "description": "Lower latency"

251 }],255 }],

252 "inputModalities": ["text", "image"],256 "inputModalities": ["text", "image"],

259 263

260Each model entry can include:264Each model entry can include:

261 265

262- `reasoningEffort` - supported effort options for the model.266- `supportedReasoningEfforts` - supported effort options for the model.

263- `defaultReasoningEffort` - suggested default effort for clients.267- `defaultReasoningEffort` - suggested default effort for clients.

264- `upgrade` - optional recommended upgrade model id for migration prompts in clients.268- `upgrade` - optional recommended upgrade model id for migration prompts in clients.

269- `upgradeInfo` - optional upgrade metadata for migration prompts in clients.

265- `hidden` - whether the model is hidden from the default picker list.270- `hidden` - whether the model is hidden from the default picker list.

266- `inputModalities` - supported input types for the model (for example `text`, `image`).271- `inputModalities` - supported input types for the model (for example `text`, `image`).

267- `supportsPersonality` - whether the model supports personality-specific instructions such as `/personality`.272- `supportsPersonality` - whether the model supports personality-specific instructions such as `/personality`.

299- `thread/list` supports cursor pagination plus `modelProviders`, `sourceKinds`, `archived`, and `cwd` filtering.304- `thread/list` supports cursor pagination plus `modelProviders`, `sourceKinds`, `archived`, and `cwd` filtering.

300- `thread/loaded/list` returns the thread IDs currently in memory.305- `thread/loaded/list` returns the thread IDs currently in memory.

301- `thread/archive` moves the thread's persisted JSONL log into the archived directory.306- `thread/archive` moves the thread's persisted JSONL log into the archived directory.

307- `thread/unsubscribe` unsubscribes the current connection from a loaded thread and can trigger `thread/closed`.

302- `thread/unarchive` restores an archived thread rollout back into the active sessions directory.308- `thread/unarchive` restores an archived thread rollout back into the active sessions directory.

303- `thread/compact/start` triggers compaction and returns `{}` immediately.309- `thread/compact/start` triggers compaction and returns `{}` immediately.

304- `thread/rollback` drops the last N turns from the in-memory context and records a rollback marker in the thread's persisted JSONL log.310- `thread/rollback` drops the last N turns from the in-memory context and records a rollback marker in the thread's persisted JSONL log.

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

314 "approvalPolicy": "never",320 "approvalPolicy": "never",

315 "sandbox": "workspaceWrite",321 "sandbox": "workspaceWrite",

316 "personality": "friendly"322 "personality": "friendly",

323 "serviceName": "my_app_server_client"

317} }324} }

318{ "id": 10, "result": {325{ "id": 10, "result": {

319 "thread": {326 "thread": {

320 "id": "thr_123",327 "id": "thr_123",

321 "preview": "",328 "preview": "",

329 "ephemeral": false,

322 "modelProvider": "openai",330 "modelProvider": "openai",

323 "createdAt": 1730910000331 "createdAt": 1730910000

324 }332 }

326{ "method": "thread/started", "params": { "thread": { "id": "thr_123" } } }334{ "method": "thread/started", "params": { "thread": { "id": "thr_123" } } }

327```335```

328 336

337`serviceName` is optional. Set it when you want app-server to tag thread-level metrics with your integration's service name.

338

329To continue a stored session, call `thread/resume` with the `thread.id` you recorded earlier. The response shape matches `thread/start`. You can also pass the same configuration overrides supported by `thread/start`, such as `personality`:339To continue a stored session, call `thread/resume` with the `thread.id` you recorded earlier. The response shape matches `thread/start`. You can also pass the same configuration overrides supported by `thread/start`, such as `personality`:

330 340

331```json341```json

333 "threadId": "thr_123",343 "threadId": "thr_123",

334 "personality": "friendly"344 "personality": "friendly"

335} }345} }

336{ "id": 11, "result": { "thread": { "id": "thr_123" } } }346{ "id": 11, "result": { "thread": { "id": "thr_123", "name": "Bug bash notes", "ephemeral": false } } }

337```347```

338 348

339Resuming a thread doesn't update `thread.updatedAt` (or the rollout file's modified time) by itself. The timestamp updates when you start a turn.349Resuming a thread doesn't update `thread.updatedAt` (or the rollout file's modified time) by itself. The timestamp updates when you start a turn.

352{ "method": "thread/started", "params": { "thread": { "id": "thr_456" } } }362{ "method": "thread/started", "params": { "thread": { "id": "thr_456" } } }

353```363```

354 364

365When a user-facing thread title has been set, app-server hydrates `thread.name` on `thread/list`, `thread/read`, `thread/resume`, `thread/unarchive`, and `thread/rollback` responses. `thread/start` and `thread/fork` may omit `name` (or return `null`) until a title is set later.

366

355### Read a stored thread (without resuming)367### Read a stored thread (without resuming)

356 368

357Use `thread/read` when you want stored thread data but don't want to resume the thread or subscribe to its events.369Use `thread/read` when you want stored thread data but don't want to resume the thread or subscribe to its events.

358 370

359- `includeTurns` - when `true`, the response includes the thread's turns; when `false` or omitted, you get the thread summary only.371- `includeTurns` - when `true`, the response includes the thread's turns; when `false` or omitted, you get the thread summary only.

372- Returned `thread` objects include runtime `status` (`notLoaded`, `idle`, `systemError`, or `active` with `activeFlags`).

360 373

361```json374```json

362{ "method": "thread/read", "id": 19, "params": { "threadId": "thr_123", "includeTurns": true } }375{ "method": "thread/read", "id": 19, "params": { "threadId": "thr_123", "includeTurns": true } }

363{ "id": 19, "result": { "thread": { "id": "thr_123", "turns": [] } } }376{ "id": 19, "result": { "thread": { "id": "thr_123", "name": "Bug bash notes", "ephemeral": false, "status": { "type": "notLoaded" }, "turns": [] } } }

364```377```

365 378

366Unlike `thread/resume`, `thread/read` doesn't load the thread into memory or emit `thread/started`.379Unlike `thread/resume`, `thread/read` doesn't load the thread into memory or emit `thread/started`.

400} }413} }

401{ "id": 20, "result": {414{ "id": 20, "result": {

402 "data": [415 "data": [

403 { "id": "thr_a", "preview": "Create a TUI", "modelProvider": "openai", "createdAt": 1730831111, "updatedAt": 1730831111 },416 { "id": "thr_a", "preview": "Create a TUI", "ephemeral": false, "modelProvider": "openai", "createdAt": 1730831111, "updatedAt": 1730831111, "name": "TUI prototype", "status": { "type": "notLoaded" } },

404 { "id": "thr_b", "preview": "Fix tests", "modelProvider": "openai", "createdAt": 1730750000, "updatedAt": 1730750000 }417 { "id": "thr_b", "preview": "Fix tests", "ephemeral": true, "modelProvider": "openai", "createdAt": 1730750000, "updatedAt": 1730750000, "status": { "type": "notLoaded" } }

405 ],418 ],

406 "nextCursor": "opaque-token-or-null"419 "nextCursor": "opaque-token-or-null"

407} }420} }

409 422

410When `nextCursor` is `null`, you have reached the final page.423When `nextCursor` is `null`, you have reached the final page.

411 424

425### Track thread status changes

426

427`thread/status/changed` is emitted whenever a loaded thread's runtime status changes. The payload includes `threadId` and the new `status`.

428

429```json

430{

431 "method": "thread/status/changed",

432 "params": {

433 "threadId": "thr_123",

434 "status": { "type": "active", "activeFlags": ["waitingOnApproval"] }

435 }

436}

437```

438

412### List loaded threads439### List loaded threads

413 440

414`thread/loaded/list` returns thread IDs currently loaded in memory.441`thread/loaded/list` returns thread IDs currently loaded in memory.

418{ "id": 21, "result": { "data": ["thr_123", "thr_456"] } }445{ "id": 21, "result": { "data": ["thr_123", "thr_456"] } }

419```446```

420 447

448### Unsubscribe from a loaded thread

449

450`thread/unsubscribe` removes the current connection's subscription to a thread. The response status is one of:

451

452- `unsubscribed` when the connection was subscribed and is now removed.

453- `notSubscribed` when the connection was not subscribed to that thread.

454- `notLoaded` when the thread is not loaded.

455

456If this was the last subscriber, the server unloads the thread and emits a `thread/status/changed` transition to `notLoaded` plus `thread/closed`.

457

458```json

459{ "method": "thread/unsubscribe", "id": 22, "params": { "threadId": "thr_123" } }

460{ "id": 22, "result": { "status": "unsubscribed" } }

461{ "method": "thread/status/changed", "params": {

462 "threadId": "thr_123",

463 "status": { "type": "notLoaded" }

464} }

465{ "method": "thread/closed", "params": { "threadId": "thr_123" } }

466```

467

421### Archive a thread468### Archive a thread

422 469

423Use `thread/archive` to move the persisted thread log (stored as a JSONL file on disk) into the archived sessions directory.470Use `thread/archive` to move the persisted thread log (stored as a JSONL file on disk) into the archived sessions directory.

425```json472```json

426{ "method": "thread/archive", "id": 22, "params": { "threadId": "thr_b" } }473{ "method": "thread/archive", "id": 22, "params": { "threadId": "thr_b" } }

427{ "id": 22, "result": {} }474{ "id": 22, "result": {} }

475{ "method": "thread/archived", "params": { "threadId": "thr_b" } }

428```476```

429 477

430Archived threads won't appear in future calls to `thread/list` unless you pass `archived: true`.478Archived threads won't appear in future calls to `thread/list` unless you pass `archived: true`.

435 483

436```json484```json

437{ "method": "thread/unarchive", "id": 24, "params": { "threadId": "thr_b" } }485{ "method": "thread/unarchive", "id": 24, "params": { "threadId": "thr_b" } }

438{ "id": 24, "result": { "thread": { "id": "thr_b" } } }486{ "id": 24, "result": { "thread": { "id": "thr_b", "name": "Bug bash notes" } } }

487{ "method": "thread/unarchived", "params": { "threadId": "thr_b" } }

439```488```

440 489

441### Trigger thread compaction490### Trigger thread compaction

449{ "id": 25, "result": {} }498{ "id": 25, "result": {} }

450```499```

451 500

501### Roll back recent turns

502

503Use `thread/rollback` to remove the last `numTurns` entries from the in-memory context and persist a rollback marker in the rollout log. The returned `thread` includes `turns` populated after the rollback.

504

505```json

506{ "method": "thread/rollback", "id": 26, "params": { "threadId": "thr_b", "numTurns": 1 } }

507{ "id": 26, "result": { "thread": { "id": "thr_b", "name": "Bug bash notes", "ephemeral": false } } }

508```

509

452## Turns510## Turns

453 511

454The `input` field accepts a list of items:512The `input` field accepts a list of items:

478}536}

479```537```

480 538

539On macOS, `includePlatformDefaults: true` appends a curated platform-default Seatbelt policy for restricted-read sessions. This improves tool compatibility without broadly allowing all of `/System`.

540

481Examples:541Examples:

482 542

483```json543```json

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

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

656 716

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

718

719Use `configRequirements/read` to inspect the effective admin requirements loaded from `requirements.toml` and/or MDM.

720

721```json

722{ "method": "configRequirements/read", "id": 52, "params": {} }

723{ "id": 52, "result": {

724 "requirements": {

725 "allowedApprovalPolicies": ["onRequest", "unlessTrusted"],

726 "allowedSandboxModes": ["readOnly", "workspaceWrite"],

727 "featureRequirements": {

728 "personality": true,

729 "unified_exec": false

730 },

731 "network": {

732 "enabled": true,

733 "allowedDomains": ["api.openai.com"],

734 "allowUnixSockets": ["/tmp/example.sock"],

735 "dangerouslyAllowAllUnixSockets": false

736 }

737 }

738} }

739```

740

741`result.requirements` is `null` when no requirements are configured. See the docs on [`requirements.toml`](https://developers.openai.com/codex/config-reference#requirementstoml) for details on supported keys and values.

742

743### Windows sandbox setup (`windowsSandbox/setupStart`)

744

745Custom Windows clients can trigger sandbox setup asynchronously instead of blocking on startup checks.

746

747```json

748{ "method": "windowsSandbox/setupStart", "id": 53, "params": { "mode": "elevated" } }

749{ "id": 53, "result": { "started": true } }

750```

751

752App-server starts setup in the background and later emits a completion notification:

753

754```json

755{

756 "method": "windowsSandbox/setupCompleted",

757 "params": { "mode": "elevated", "success": true, "error": null }

758}

759```

760

761Modes:

762

763- `elevated` - run the elevated Windows sandbox setup path.

764- `unelevated` - run the legacy setup/preflight path.

765

657## Events766## Events

658 767

659Event notifications are the server-initiated stream for thread lifecycles, turn lifecycles, and the items within them. After you start or resume a thread, keep reading the active transport stream for `thread/started`, `turn/*`, and `item/*` notifications.768Event notifications are the server-initiated stream for thread lifecycles, turn lifecycles, and the items within them. After you start or resume a thread, keep reading the active transport stream for `thread/started`, `thread/archived`, `thread/unarchived`, `thread/closed`, `thread/status/changed`, `turn/*`, `item/*`, and `serverRequest/resolved` notifications.

660 769

661### Notification opt-out770### Notification opt-out

662 771

674- `fuzzyFileSearch/sessionUpdated` - `{ sessionId, query, files }` with the current matches for the active query.783- `fuzzyFileSearch/sessionUpdated` - `{ sessionId, query, files }` with the current matches for the active query.

675- `fuzzyFileSearch/sessionCompleted` - `{ sessionId }` once indexing and matching for that query completes.784- `fuzzyFileSearch/sessionCompleted` - `{ sessionId }` once indexing and matching for that query completes.

676 785

786### Windows sandbox setup events

787

788- `windowsSandbox/setupCompleted` - `{ mode, success, error }` emitted after a `windowsSandbox/setupStart` request finishes.

789

677### Turn events790### Turn events

678 791

679- `turn/started` - `{ turn }` with the turn id, empty `items`, and `status: "inProgress"`.792- `turn/started` - `{ turn }` with the turn id, empty `items`, and `status: "inProgress"`.

689`ThreadItem` is the tagged union carried in turn responses and `item/*` notifications. Common item types include:802`ThreadItem` is the tagged union carried in turn responses and `item/*` notifications. Common item types include:

690 803

691- `userMessage` - `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).804- `userMessage` - `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).

692- `agentMessage` - `{id, text}` containing the accumulated agent reply.805- `agentMessage` - `{id, text, phase?}` containing the accumulated agent reply. When present, `phase` uses Responses API wire values (`commentary`, `final_answer`).

693- `plan` - `{id, text}` containing proposed plan text in plan mode. Treat the final `plan` item from `item/completed` as authoritative.806- `plan` - `{id, text}` containing proposed plan text in plan mode. Treat the final `plan` item from `item/completed` as authoritative.

694- `reasoning` - `{id, summary, content}` where `summary` holds streamed reasoning summaries and `content` holds raw reasoning blocks.807- `reasoning` - `{id, summary, content}` where `summary` holds streamed reasoning summaries and `content` holds raw reasoning blocks.

695- `commandExecution` - `{id, command, cwd, status, commandActions, aggregatedOutput?, exitCode?, durationMs?}`.808- `commandExecution` - `{id, command, cwd, status, commandActions, aggregatedOutput?, exitCode?, durationMs?}`.

696- `fileChange` - `{id, changes, status}` describing proposed edits; `changes` list `{path, kind, diff}`.809- `fileChange` - `{id, changes, status}` describing proposed edits; `changes` list `{path, kind, diff}`.

697- `mcpToolCall` - `{id, server, tool, status, arguments, result?, error?}`.810- `mcpToolCall` - `{id, server, tool, status, arguments, result?, error?}`.

811- `dynamicToolCall` - `{id, tool, arguments, status, contentItems?, success?, durationMs?}` for client-executed dynamic tool invocations.

698- `collabToolCall` - `{id, tool, status, senderThreadId, receiverThreadId?, newThreadId?, prompt?, agentStatus?}`.812- `collabToolCall` - `{id, tool, status, senderThreadId, receiverThreadId?, newThreadId?, prompt?, agentStatus?}`.

699- `webSearch` - `{id, query, action?}` for web search requests issued by the agent.813- `webSearch` - `{id, query, action?}` for web search requests issued by the agent.

700- `imageView` - `{id, path}` emitted when the agent invokes the image viewer tool.814- `imageView` - `{id, path}` emitted when the agent invokes the image viewer tool.

751Order of messages:865Order of messages:

752 866

7531. `item/started` shows the pending `commandExecution` item with `command`, `cwd`, and other fields.8671. `item/started` shows the pending `commandExecution` item with `command`, `cwd`, and other fields.

7542. `item/commandExecution/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, optional `command`, optional `cwd`, optional `commandActions`, and optional `proposedExecpolicyAmendment`.8682. `item/commandExecution/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, optional `command`, optional `cwd`, optional `commandActions`, optional `proposedExecpolicyAmendment`, optional `networkApprovalContext`, and optional `availableDecisions`. When `initialize.params.capabilities.experimentalApi = true`, the payload can also include experimental `additionalPermissions` describing requested per-command sandbox access. Any filesystem paths inside `additionalPermissions` are absolute on the wire.

7553. Client responds with one of the command execution approval decisions above.8693. Client responds with one of the command execution approval decisions above.

7564. `item/completed` returns the final `commandExecution` item with `status: completed | failed | declined`.8704. `serverRequest/resolved` confirms that the pending request has been answered or cleared.

8715. `item/completed` returns the final `commandExecution` item with `status: completed | failed | declined`.

872

873When `networkApprovalContext` is present, the prompt is for managed network access (not a general shell-command approval). The current v2 schema exposes the target `host` and `protocol`; clients should render a network-specific prompt and not rely on `command` being a user-meaningful shell command preview.

874

875Codex groups concurrent network approval prompts by destination (`host`, protocol, and port). The app-server may therefore send one prompt that unblocks multiple queued requests to the same destination, while different ports on the same host are treated separately.

757 876

758### File change approvals877### File change approvals

759 878

7621. `item/started` emits a `fileChange` item with proposed `changes` and `status: "inProgress"`.8811. `item/started` emits a `fileChange` item with proposed `changes` and `status: "inProgress"`.

7632. `item/fileChange/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, and optional `grantRoot`.8822. `item/fileChange/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, and optional `grantRoot`.

7643. Client responds with one of the file change approval decisions above.8833. Client responds with one of the file change approval decisions above.

7654. `item/completed` returns the final `fileChange` item with `status: completed | failed | declined`.8844. `serverRequest/resolved` confirms that the pending request has been answered or cleared.

8855. `item/completed` returns the final `fileChange` item with `status: completed | failed | declined`.

886

887### `tool/requestUserInput`

888

889When the client responds to `item/tool/requestUserInput`, app-server emits `serverRequest/resolved` with `{ threadId, requestId }`. If the pending request is cleared by turn start, turn completion, or turn interruption before the client answers, the server emits the same notification for that cleanup.

890

891### Dynamic tool calls (experimental)

892

893`dynamicTools` on `thread/start` and the corresponding `item/tool/call` request or response flow are experimental APIs.

894

895When a dynamic tool is invoked during a turn, app-server emits:

896

8971. `item/started` with `item.type = "dynamicToolCall"`, `status = "inProgress"`, plus `tool` and `arguments`.

8982. `item/tool/call` as a server request to the client.

8993. The client response payload with returned content items.

9004. `item/completed` with `item.type = "dynamicToolCall"`, the final `status`, and any returned `contentItems` or `success` value.

766 901

767### MCP tool-call approvals (apps)902### MCP tool-call approvals (apps)

768 903

769App (connector) tool calls can also require approval. When an app tool call has side effects, the server may elicit approval with `tool/requestUserInput` and options such as **Accept**, **Decline**, and **Cancel**. If the user declines or cancels, the related `mcpToolCall` item completes with an error instead of running the tool.904App (connector) tool calls can also require approval. When an app tool call has side effects, the server may elicit approval with `tool/requestUserInput` and options such as **Accept**, **Decline**, and **Cancel**. Destructive tool annotations always trigger approval even when the tool also advertises less-privileged hints. If the user declines or cancels, the related `mcpToolCall` item completes with an error instead of running the tool.

770 905

771## Skills906## Skills

772 907

863 998

864## Apps (connectors)999## Apps (connectors)

865 1000

866Use `app/list` to fetch available apps. In the CLI/TUI, `/apps` is the user-facing picker; in custom clients, call `app/list` directly. Each entry includes both `isAccessible` (available to the user) and `isEnabled` (enabled in `config.toml`) so clients can distinguish install/access from local enabled state.1001Use `app/list` to fetch available apps. In the CLI/TUI, `/apps` is the user-facing picker; in custom clients, call `app/list` directly. Each entry includes both `isAccessible` (available to the user) and `isEnabled` (enabled in `config.toml`) so clients can distinguish install/access from local enabled state. App entries can also include optional `branding`, `appMetadata`, and `labels` fields.

867 1002

868```json1003```json

869{ "method": "app/list", "id": 50, "params": {1004{ "method": "app/list", "id": 50, "params": {

879 "name": "Demo App",1014 "name": "Demo App",

880 "description": "Example connector for documentation.",1015 "description": "Example connector for documentation.",

881 "logoUrl": "https://example.com/demo-app.png",1016 "logoUrl": "https://example.com/demo-app.png",

1017 "logoUrlDark": null,

1018 "distributionChannel": null,

1019 "branding": null,

1020 "appMetadata": null,

1021 "labels": null,

882 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",1022 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",

883 "isAccessible": true,1023 "isAccessible": true,

884 "isEnabled": true1024 "isEnabled": true

904 "name": "Demo App",1044 "name": "Demo App",

905 "description": "Example connector for documentation.",1045 "description": "Example connector for documentation.",

906 "logoUrl": "https://example.com/demo-app.png",1046 "logoUrl": "https://example.com/demo-app.png",

1047 "logoUrlDark": null,

1048 "distributionChannel": null,

1049 "branding": null,

1050 "appMetadata": null,

1051 "labels": null,

907 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",1052 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",

908 "isAccessible": true,1053 "isAccessible": true,

909 "isEnabled": true1054 "isEnabled": true

936}1081}

937```1082```

938 1083

1084### Config RPC examples for app settings

1085

1086Use `config/read`, `config/value/write`, and `config/batchWrite` to inspect or update app controls in `config.toml`.

1087

1088Read the effective app config shape (including `_default` and per-tool overrides):

1089

1090```json

1091{ "method": "config/read", "id": 60, "params": { "includeLayers": false } }

1092{ "id": 60, "result": {

1093 "config": {

1094 "apps": {

1095 "_default": {

1096 "enabled": true,

1097 "destructive_enabled": true,

1098 "open_world_enabled": true

1099 },

1100 "google_drive": {

1101 "enabled": true,

1102 "destructive_enabled": false,

1103 "default_tools_approval_mode": "prompt",

1104 "tools": {

1105 "files/delete": { "enabled": false, "approval_mode": "approve" }

1106 }

1107 }

1108 }

1109 }

1110} }

1111```

1112

1113Update a single app setting:

1114

1115```json

1116{

1117 "method": "config/value/write",

1118 "id": 61,

1119 "params": {

1120 "keyPath": "apps.google_drive.default_tools_approval_mode",

1121 "value": "prompt",

1122 "mergeStrategy": "replace"

1123 }

1124}

1125```

1126

1127Apply multiple app edits atomically:

1128

1129```json

1130{

1131 "method": "config/batchWrite",

1132 "id": 62,

1133 "params": {

1134 "edits": [

1135 {

1136 "keyPath": "apps._default.destructive_enabled",

1137 "value": false,

1138 "mergeStrategy": "upsert"

1139 },

1140 {

1141 "keyPath": "apps.google_drive.tools.files/delete.approval_mode",

1142 "value": "approve",

1143 "mergeStrategy": "upsert"

1144 }

1145 ]

1146 }

1147}

1148```

1149

1150### Detect and import external agent config

1151

1152Use `externalAgentConfig/detect` to discover migratable external-agent artifacts, then pass the selected entries to `externalAgentConfig/import`.

1153

1154Detection example:

1155

1156```json

1157{ "method": "externalAgentConfig/detect", "id": 63, "params": {

1158 "includeHome": true,

1159 "cwds": ["/Users/me/project"]

1160} }

1161{ "id": 63, "result": {

1162 "items": [

1163 {

1164 "itemType": "AGENTS_MD",

1165 "description": "Import /Users/me/project/CLAUDE.md to /Users/me/project/AGENTS.md.",

1166 "cwd": "/Users/me/project"

1167 },

1168 {

1169 "itemType": "SKILLS",

1170 "description": "Copy skill folders from /Users/me/.claude/skills to /Users/me/.agents/skills.",

1171 "cwd": null

1172 }

1173 ]

1174} }

1175```

1176

1177Import example:

1178

1179```json

1180{ "method": "externalAgentConfig/import", "id": 64, "params": {

1181 "migrationItems": [

1182 {

1183 "itemType": "AGENTS_MD",

1184 "description": "Import /Users/me/project/CLAUDE.md to /Users/me/project/AGENTS.md.",

1185 "cwd": "/Users/me/project"

1186 }

1187 ]

1188} }

1189{ "id": 64, "result": {} }

1190```

1191

1192Supported `itemType` values are `AGENTS_MD`, `CONFIG`, `SKILLS`, and `MCP_SERVER_CONFIG`. Detection returns only items that still have work to do. For example, AGENTS migration is skipped when `AGENTS.md` already exists and is non-empty, and skill imports do not overwrite existing skill directories.

1193

939## Auth endpoints1194## Auth endpoints

940 1195

941The JSON-RPC auth/account surface exposes request/response methods plus server-initiated notifications (no `id`). Use these to determine auth state, start or cancel logins, logout, and inspect ChatGPT rate limits.1196The JSON-RPC auth/account surface exposes request/response methods plus server-initiated notifications (no `id`). Use these to determine auth state, start or cancel logins, logout, and inspect ChatGPT rate limits.

app/automations.md +1 −1

Details

62 62

63If you are in a managed environment, admins can restrict these behaviors using63If you are in a managed environment, admins can restrict these behaviors using

64admin-enforced requirements. For example, they can disallow `approval_policy = "never"` or constrain allowed sandbox modes. See64admin-enforced requirements. For example, they can disallow `approval_policy = "never"` or constrain allowed sandbox modes. See

~~65[Admin-enforced requirements (`requirements.toml`)](https://developers.openai.com/codex/security#admin-enforced-requirements-requirementstoml).~~65[Admin-enforced requirements (`requirements.toml`)](https://developers.openai.com/codex/enterprise/managed-configuration#admin-enforced-requirements-requirementstoml).

66 66

67Automations use `approval_policy = "never"` when your organization policy67Automations use `approval_policy = "never"` when your organization policy

68allows it. If `approval_policy = "never"` is disallowed by admin requirements,68allows it. If `approval_policy = "never"` is disallowed by admin requirements,

app/features.md +15 −3

Details

14session in a specific directory.14session in a specific directory.

15 15

16If you work in a single repository with two or more apps or packages, split16If you work in a single repository with two or more apps or packages, split

~~17distinct projects into separate app projects so the [sandbox](https://developers.openai.com/codex/security)~~17distinct projects into separate app projects so the [sandbox](https://developers.openai.com/codex/agent-approvals-security)

18only includes the files for that project.18only includes the files for that project.

19 19

20![Codex app showing multiple projects in the sidebar and threads in the main pane](/images/codex/app/multitask-light.webp)20![Codex app showing multiple projects in the sidebar and threads in the main pane](/images/codex/app/multitask-light.webp)

101 101

102![Integrated terminal drawer open beneath a Codex thread](/images/codex/app/integrated-terminal-light.webp)102![Integrated terminal drawer open beneath a Codex thread](/images/codex/app/integrated-terminal-light.webp)

103 103

104## Native Windows sandbox

105

106On Windows, Codex can run natively in PowerShell with a native Windows sandbox

107instead of requiring WSL or a virtual machine. This lets you stay in

108Windows-native workflows while keeping bounded permissions in place.

109

110[Learn more about Windows setup and sandboxing](https://developers.openai.com/codex/app/windows).

111

112![Codex app Windows sandbox setup prompt above the message composer](/images/codex/windows/windows-sandbox-setup.webp)

113

104## Voice dictation114## Voice dictation

105 115

106Use your voice to prompt Codex. Hold <kbd>Ctrl</kbd>+<kbd>M</kbd> while the composer is visible and start talking. Your voice will be transcribed. Edit the transcribed prompt or hit send to have Codex start work.116Use your voice to prompt Codex. Hold <kbd>Ctrl</kbd>+<kbd>M</kbd> while the composer is visible and start talking. Your voice will be transcribed. Edit the transcribed prompt or hit send to have Codex start work.

152opening separate projects or using worktrees rather than asking Codex to roam162opening separate projects or using worktrees rather than asking Codex to roam

153outside the project root.163outside the project root.

154 164

155For details on how Codex handles sandboxing, check out the [security documentation](https://developers.openai.com/codex/security).165For a high-level overview, see [Sandboxing](https://developers.openai.com/codex/concepts/sandboxing). For

166configuration details, see the

167[agent approvals & security documentation](https://developers.openai.com/codex/agent-approvals-security).

156 168

157## MCP support169## MCP support

158 170

165 177

166Codex ships with a first-party web search tool. For local tasks in the Codex IDE Extension, Codex178Codex ships with a first-party web search tool. For local tasks in the Codex IDE Extension, Codex

167enables web search by default and serves results from a web search cache. If you configure your179enables web search by default and serves results from a web search cache. If you configure your

168sandbox for [full access](https://developers.openai.com/codex/security), web search defaults to live results. See180sandbox for [full access](https://developers.openai.com/codex/agent-approvals-security), web search defaults to live results. See

169[Config basics](https://developers.openai.com/codex/config-basic) to disable web search or switch to live results that fetch the181[Config basics](https://developers.openai.com/codex/config-basic) to disable web search or switch to live results that fetch the

170most recent data.182most recent data.

171 183

app/settings.md +1 −1

Details

24 24

25Codex agents in the app inherit the same configuration as the IDE and CLI extension.25Codex agents in the app inherit the same configuration as the IDE and CLI extension.

26Use the in-app controls for common settings, or edit `config.toml` for advanced26Use the in-app controls for common settings, or edit `config.toml` for advanced

~~27options. See [Codex security](https://developers.openai.com/codex/security) and~~27options. See [Codex security](https://developers.openai.com/codex/agent-approvals-security) and

28[config basics](https://developers.openai.com/codex/config-basic) for more detail.28[config basics](https://developers.openai.com/codex/config-basic) for more detail.

29 29

30## Git30## Git

app/troubleshooting.md +4 −2

Details

32### Only some threads appear in the sidebar32### Only some threads appear in the sidebar

33 33

34The sidebar allows filtering of threads depending on the state of a project. If34The sidebar allows filtering of threads depending on the state of a project. If

~~35you’re missing threads, check whether you have any filters applied by clicking~~35you're missing threads, click the filter icon next to the **Threads** label and

~~36the filter icon next to the **Threads** label.~~36switch to Chronological. If you still don't see the thread, open

37[Settings](codex://settings) and check the archived chats or archived threads

38section.

37 39

38### Code doesn't run on a worktree40### Code doesn't run on a worktree

39 41

app/windows.md +202 −0 added

Details

1# Windows

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

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

5It runs natively on Windows using PowerShell and the

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

7run in [Windows Subsystem for Linux (WSL)](#windows-subsystem-for-linux-wsl).

9![Codex app for Windows showing a project sidebar, active thread, and review pane](/images/codex/windows/codex-windows-light.webp)

11## Download and update the Codex app

13Download the Codex app from the

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

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

18To update the app, open the Microsoft Store, go to **Downloads**, and click

19**Check for updates**. The Store installs the latest version afterward.

21For enterprises, administrators can deploy the app with Microsoft Store app

22distribution through enterprise management tools.

24If you prefer a command-line install path, or need an alternative to opening

25the Microsoft Store UI, run:

27```powershell

28winget install Codex -s msstore

29```

31## Customize for your dev setup

33### Preferred editor

35Choose a default app for **Open**, such as Visual Studio, VS Code, or another

36editor. You can override that choice per project. If you already picked a

37different app from the **Open** menu for a project, that project-specific

38choice takes precedence.

40![Codex app settings showing the default Open In app on Windows](/images/codex/windows/open-in-windows-light.webp)

42### Integrated terminal

44You can also choose the default integrated terminal. Depending on what you have

45installed, options include:

47- PowerShell

48- Command Prompt

49- Git Bash

50- WSL

52This change applies only to new terminal sessions. If you already have an

53integrated terminal open, restart the app or start a new thread before

54expecting the new default terminal to appear.

56![Codex app settings showing the integrated terminal selection on Windows](/images/codex/windows/integrated-shell-light.webp)

58## Windows Subsystem for Linux (WSL)

60By default, the Codex app uses the Windows-native agent. That means the agent

61runs commands in PowerShell. The app can still work with projects that live in

62Windows Subsystem for Linux (WSL) by using the `wsl` CLI when needed.

64If you want to add a project from the WSL filesystem, click **Add new project**

65or press <kbd>Ctrl</kbd>+<kbd>O</kbd>, then type `\\wsl$\` into the File

66Explorer window. From there, choose your Linux distribution and the folder you

67want to open.

69If you plan to keep using the Windows-native agent, prefer storing projects on

70your Windows filesystem and accessing them from WSL through

71`/mnt/<drive>/...`. This setup is more reliable than opening projects

72directly from the WSL filesystem.

74If you want the agent itself to run in WSL, open **[Settings](codex://settings)**,

75switch the agent from Windows native to WSL, and **restart the app**. The

76change doesn't take effect until you restart. Your projects should remain in

77place after restart.

79![Codex app settings showing the agent selector with Windows native and WSL options](/images/codex/windows/wsl-select-light.webp)

81You configure the integrated terminal independently from the agent. See

82[Customize for your dev setup](#customize-for-your-dev-setup) for the

83terminal options. You can keep the agent in WSL and still use PowerShell in the

84terminal, or use WSL for both, depending on your workflow.

86## Useful developer tools

88Codex works best when a few common developer tools are already installed:

90- **Git**: Powers the review panel in the Codex app and lets you inspect or

91 revert changes.

92- **Node.js**: A common tool that the agent uses to perform tasks more

93 efficiently.

94- **Python**: A common tool that the agent uses to perform tasks more

95 efficiently.

96- **.NET SDK**: Useful when you want to build native Windows apps.

97- **GitHub CLI**: Powers GitHub-specific functionality in the Codex app.

99Install them with the default Windows package manager `winget` by pasting this

100into the [integrated terminal](https://developers.openai.com/codex/app/features#integrated-terminal) or

101asking Codex to install them:

102

103```powershell

104winget install --id Git.Git

105winget install --id OpenJS.NodeJS.LTS

106winget install --id Python.Python.3.14

107winget install --id Microsoft.DotNet.SDK.10

108winget install --id GitHub.cli

109```

110

111After installing GitHub CLI, run `gh auth login` to enable GitHub features in

112the app.

113

114If you need a different Python or .NET version, change the package IDs to the

115version you want.

116

117## Troubleshooting and FAQ

118

119### Run commands with elevated permissions

120

121If you need Codex to run commands with elevated permissions, start the Codex app

122itself as an administrator. After installation, open the Start menu, find

123Codex, and choose Run as administrator. The Codex agent inherits that

124permission level.

125

126### PowerShell execution policy blocks commands

127

128If you have never used tools such as Node.js or `npm` in PowerShell before, the

129Codex agent or integrated terminal may hit execution policy errors.

130

131This can also happen if Codex creates PowerShell scripts for you. In that case,

132you may need a less restrictive execution policy before PowerShell will run

133them.

134

135An error may look something like this:

136

137```text

138npm.ps1 cannot be loaded because running scripts is disabled on this system.

139```

140

141A common fix is to set the execution policy to `RemoteSigned`:

142

143```powershell

144Set-ExecutionPolicy -ExecutionPolicy RemoteSigned

145```

146

147For details and other options, check Microsoft's

148[execution policy guide](https://learn.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_execution_policies)

149before changing the policy.

150

151### Local environment scripts on Windows

152

153If your [local environment](https://developers.openai.com/codex/app/local-environments) uses cross-platform

154commands such as `npm` scripts, you can keep one shared setup script or

155set of actions for every platform.

156

157If you need Windows-specific behavior, create Windows-specific setup scripts or

158Windows-specific actions.

159

160Actions run in the environment used by your integrated terminal. See

161[Customize for your dev setup](#customize-for-your-dev-setup).

162

163Local setup scripts run in the agent environment: WSL if the agent uses WSL,

164and PowerShell otherwise.

165

166### Share config, auth, and sessions with WSL

167

168The Windows app uses the same Codex home directory as native Codex on Windows:

169`%USERPROFILE%\.codex`.

170

171If you also run the Codex CLI inside WSL, the CLI uses the Linux home

172directory by default, so it does not automatically share configuration, cached

173auth, or session history with the Windows app.

174

175To share them, use one of these approaches:

176

177- Sync WSL `~/.codex` with `%USERPROFILE%\.codex` on your file system.

178- Point WSL at the Windows Codex home directory by setting `CODEX_HOME`:

179

180```bash

181export CODEX_HOME=/mnt/c/Users/<windows-user>/.codex

182```

183

184If you want that setting in every shell, add it to your WSL shell profile, such

185as `~/.bashrc` or `~/.zshrc`.

186

187### Git features are unavailable

188

189If you don't have Git installed natively on Windows, the app can't use some

190features. Install it with `winget install Git.Git` from PowerShell or `cmd.exe`.

191

192### Git isn't detected for projects opened from `\\wsl$`

193

194For now, if you want to use the Windows-native agent with a project that is

195also accessible from WSL, the most reliable workaround is to store the project

196on the native Windows drive and access it in WSL through `/mnt/<drive>/...`.

197

198### Cmder is not listed in the open dialog

199

200If Cmder is installed but doesn’t show in Codex’s open dialog, add it to the

201Windows Start Menu: right-click Cmder and choose **Add to Start**, then restart

202Codex or reboot.

app/worktrees.md +45 −43

Details

1# Worktrees1# Worktrees

2 2

3In the Codex app, worktrees let Codex run multiple independent tasks in the same project without interfering with each other. For Git repositories, [automations](https://developers.openai.com/codex/app/automations) run on dedicated background worktrees so they don’t conflict with your ongoing work. In non-version-controlled projects, automations run directly in the project directory. You can also start threads on a worktree manually.3In the Codex app, worktrees let Codex run multiple independent tasks in the same project without interfering with each other. For Git repositories, [automations](https://developers.openai.com/codex/app/automations) run on dedicated background worktrees so they don't conflict with your ongoing work. In non-version-controlled projects, automations run directly in the project directory. You can also start threads on a worktree manually, and use Handoff to move a thread between Local and Worktree.

4 4

5## What's a worktree5## What's a worktree

6 6

10 10

11- **Local checkout**: The repository that you created. Sometimes just referred to as **Local** in the Codex app.11- **Local checkout**: The repository that you created. Sometimes just referred to as **Local** in the Codex app.

12- **Worktree**: A [Git worktree](https://git-scm.com/docs/git-worktree) that was created from your local checkout in the Codex app.12- **Worktree**: A [Git worktree](https://git-scm.com/docs/git-worktree) that was created from your local checkout in the Codex app.

13- **Handoff**: The flow that moves a thread between Local and Worktree. Codex handles the Git operations required to move your work safely between them.

13 14

14## Why use a worktree15## Why use a worktree

15 16

~~161. Work in parallel with Codex without breaking each other as you work.~~171. Work in parallel with Codex without disturbing your current Local setup.

~~172. Start a thread unrelated to your current work~~182. Queue up background work while you stay focused on the foreground.

~~18 - Staging area to queue up work you want Codex to start but aren’t ready to test yet.~~193. Move a thread into Local later when you're ready to inspect, test, or collaborate more directly.

19 20

20## Getting started21## Getting started

21 22

313. Submit your prompt323. Submit your prompt

32 33

33 Submit your task and Codex will create a Git worktree based on the branch you selected. By default, Codex works in a ["detached HEAD"](https://git-scm.com/docs/git-checkout#_detached_head).34 Submit your task and Codex will create a Git worktree based on the branch you selected. By default, Codex works in a ["detached HEAD"](https://git-scm.com/docs/git-checkout#_detached_head).

~~344. Verify your changes~~354. Choose where to keep working

35 36

~~36 When you’re ready, follow one of the paths [below](#verifying-and-pushing-workflow-changes)~~37 When you’re ready, you can either keep working directly on the worktree or hand the thread off to your local checkout. Handing off to or from local will move your thread *and* code so you can continue in the other checkout.

~~37 based on your project and flow.~~

38 38

~~39## Verifying and pushing workflow changes~~39## Working between Local and Worktree

40 40

41Worktrees look and feel much like your local checkout. But **Git only allows a branch to be checked out in one place at a time**. If you check out a branch on a worktree, you **can’t** check it out in your local checkout at the same time, and vice versa.41Worktrees look and feel much like your local checkout. The difference is where they fit into your flow. You can think of Local as the foreground and Worktree as the background. Handoff lets you move a thread between them.

42 42

~~43Because of this, choose how you want to verify and commit changes Codex made on a worktree:~~43Under the hood, Handoff handles the Git operations required to move work between two checkouts safely. This matters because **Git only allows a branch to be checked out in one place at a time**. If you check out a branch on a worktree, you **can't** check it out in your local checkout at the same time, and vice versa.

45In practice, there are two common paths:

44 46

451. [Work exclusively on the worktree](#option-1-working-on-the-worktree). This path works best when you can verify changes directly on the worktree, for example because you have dependencies and tools installed using a [local environment setup script](https://developers.openai.com/codex/app/local-environments).471. [Work exclusively on the worktree](#option-1-working-on-the-worktree). This path works best when you can verify changes directly on the worktree, for example because you have dependencies and tools installed using a [local environment setup script](https://developers.openai.com/codex/app/local-environments).

462. [Work in your local checkout](#option-2-working-in-your-local-checkout). Use this when you need to bring changes back into your main checkout, for example because you can run only one instance of your app.482. [Hand the thread off to Local](#option-2-handing-a-thread-off-to-local). Use this when you want to bring the thread into the foreground, for example because you want to inspect changes in your usual IDE or can run only one instance of your app.

47 49

48### Option 1: Working on the worktree50### Option 1: Working on the worktree

49 51

57 59

58Remember, if you create a branch on a worktree, you can't check it out in any other worktree, including your local checkout.60Remember, if you create a branch on a worktree, you can't check it out in any other worktree, including your local checkout.

59 61

~~60If you plan to keep working on this branch, you can [add it to the sidebar](#adding-a-worktree-to-the-sidebar). Otherwise, archive the thread after you’re done so the worktree can be deleted.~~62### Option 2: Handing a thread off to Local

~~62### Option 2: Working in your local checkout~~

63 63

~~64If you don’t want to verify your changes directly on the worktree and instead check them out on your local checkout, click **Sync with local** in the header of your thread.~~64If you want to bring a thread into the foreground, click **Hand off** in the header of your thread and move it to **Local**.

65 65

~~66You will be presented with the option of creating a new branch or syncing to an existing branch.~~66This path works well when you want to read the changes in your usual IDE window, run your existing development server, or validate the work in the same environment you already use day to day.

67 67

~~68You can sync with local at any point. To do so, click **Sync with local** in the header again. From here, you can choose which direction to sync (to local or from local) and a sync method:~~68Codex handles the Git steps required to move the thread safely between the worktree and your local checkout.

69 69

~~70- **Overwrite**: Makes the destination checkout match the source checkout’s files and commit history.~~70Each thread keeps the same associated worktree over time. If you hand the thread back to a worktree later, Codex returns it to that same background environment so you can pick up where you left off.

71- **Apply**: Calculates the source changes since the nearest shared commit and applies that patch onto the destination checkout, preserving destination commit history while bringing over source code changes (not source commits).

72 71

~~73![Sync worktree dialog with options to apply or pull changes](/images/codex/app/sync-worktree-light.webp)~~72![Handoff dialog moving a thread from a worktree to Local](/images/codex/app/handoff-light.webp)

74 73

~~75You can create multiple worktrees and sync them to the same feature branch to split up your work into parallel threads.~~74You can also go the other direction. If you're already working in Local and want to free up the foreground, use **Hand off** to move the thread to a worktree. This is useful when you want Codex to keep working in the background while you switch your attention back to something else locally.

76 75

77In some cases, changes on your worktree might conflict with changes on your local checkout, for example from testing a previous worktree. In those cases, you can use the **Overwrite local** option to reset the previous changes and cleanly apply your worktree changes.76Since Handoff uses Git operations, any files that are part of your `.gitignore` file won't move with the thread.

78 77

~~79Since this process uses Git operations, any files that are part of the `.gitignore` file won’t be transferred during the sync process.~~78## Advanced details

80 79

~~81## Adding a worktree to the sidebar~~80### Codex-managed and permanent worktrees

82 81

83If you choose option one above (work on the worktree), once you have created a branch on the worktree, an option appears in the header to add the worktree to your sidebar. This promotes the worktree to a permanent home. When you do this, it will never be automatically deleted, and you can even kick off new threads from the same worktree.82By default, threads use a Codex-managed worktree. These are meant to feel lightweight and disposable. A Codex-managed worktree is typically dedicated to one thread, and Codex returns that thread to the same worktree if you hand it back there later.

84 83

~~85## Advanced details~~84If you want a long-lived environment, create a permanent worktree from the three-dot menu on a project in the sidebar. This creates a new permanent worktree as its own project. Permanent worktrees are not automatically deleted, and you can start multiple threads from the same worktree.

86 85

87### How Codex manages worktrees for you86### How Codex manages worktrees for you

88 87

89Codex will create a worktree in `$CODEX_HOME/worktrees`. The starting commit will be the `HEAD` commit of the branch selected when you start your thread. If you chose a branch with local changes, the uncommitted changes will be applied to the worktree as well. The worktree will *not* be checked out as a branch. It will be in a [detached HEAD](https://git-scm.com/docs/git-checkout#_detached_head) state. This means you can create several worktrees without polluting your branches.88Codex creates worktrees in `$CODEX_HOME/worktrees`. The starting commit will be the `HEAD` commit of the branch selected when you start your thread. If you chose a branch with local changes, the uncommitted changes will be applied to the worktree as well. The worktree will *not* be checked out as a branch. It will be in a [detached HEAD](https://git-scm.com/docs/git-checkout#_detached_head) state. This lets Codex create several worktrees without polluting your branches.

90 89

91### Branch limitations90### Branch limitations

92 91

98 97

99To resolve this, you would need to check out another branch instead of `feature/a` on the worktree.98To resolve this, you would need to check out another branch instead of `feature/a` on the worktree.

100 99

101If you plan on checking out the branch locally, try Workflow 2 ([sync with local](#option-2-working-in-your-local-checkout)).100If you plan on checking out the branch locally, use Handoff to move the thread into Local instead of trying to keep the same branch checked out in both places at once.

102 101

103Why this limitation exists102Why this limitation exists

104 103

112 111

113Worktrees can take up a lot of disk space. Each one has its own set of repository files, dependencies, build caches, etc. As a result, the Codex app tries to keep the number of worktrees to a reasonable limit.112Worktrees can take up a lot of disk space. Each one has its own set of repository files, dependencies, build caches, etc. As a result, the Codex app tries to keep the number of worktrees to a reasonable limit.

114 113

115Worktrees will never be cleaned up if:114By default, Codex keeps your most recent 15 Codex-managed worktrees. You can change this limit or turn off automatic deletion in settings if you prefer to manage disk usage yourself.

116 115

117- A pinned conversation is tied to it116Codex tries to avoid deleting worktrees that are still important. Codex-managed worktrees won't be deleted automatically if:

118- The worktree was added to the sidebar (see above)

119 117

120Worktrees are eligible for cleanup when:118- A pinned conversation is tied to it

119- The thread is still in progress

120- The worktree is a permanent worktree

121 121

122- It’s more than 4 days old122Codex-managed worktrees are deleted automatically when:

123- You have more than 10 worktrees

124 123

125When either of those conditions are met, Codex automatically cleans up a worktree when you archive a thread, or on app startup if it finds a worktree with no associated threads.124- You archive the associated thread

125- Codex needs to delete older worktrees to stay within your configured limit

126 126

127Before cleaning up a worktree, Codex will save a snapshot of the work on it that you can restore at any point in a new worktree. If you open a conversation after its worktree was cleaned up, you’ll see the option to restore it.127Before deleting a Codex-managed worktree, Codex saves a snapshot of the work on it. If you open a conversation after its worktree was deleted, you'll see the option to restore it.

128 128

129## Frequently asked questions129## Frequently asked questions

130 130

133 Not today. Codex creates worktrees under `$CODEX_HOME/worktrees` so it can133 Not today. Codex creates worktrees under `$CODEX_HOME/worktrees` so it can

134 manage them consistently.134 manage them consistently.

135 135

136Can I move a session between worktrees?136Can I move a thread between Local and Worktree?

137 137

138Not yet. If you need to change environments, you have to start a new thread in138 Yes. Use **Hand off** in the thread header to move a thread between your local

139the target environment and restate the prompt. You can use the up arrow keys139 checkout and a worktree. Codex handles the Git operations needed to move the

140in the composer to try to recover your prompt.140 thread safely between environments. If you hand a thread back to a worktree

141 later, Codex returns it to the same associated worktree.

141 142

142What happens to threads if a worktree is deleted?143What happens to threads if a worktree is deleted?

143 144

144 Threads can remain in your history even if the underlying worktree directory145 Threads can remain in your history even if the underlying worktree directory

145is cleaned up. However, Codex saves a snapshot of the worktree prior to146 is deleted. For Codex-managed worktrees, Codex saves a snapshot before

146cleaning it up and offers to restore it if you reopen the thread associated147 deleting the worktree and offers to restore it if you reopen the associated

147with it.148 thread. Permanent worktrees are not automatically deleted when you archive

149 their threads.

auth.md +22 −1

Details

9 9

10Codex cloud requires signing in with ChatGPT. The Codex CLI and IDE extension support both sign-in methods.10Codex cloud requires signing in with ChatGPT. The Codex CLI and IDE extension support both sign-in methods.

11 11

12Your sign-in method also determines which admin controls and data-handling policies apply.

14- With sign in with ChatGPT, Codex usage follows your ChatGPT workspace permissions, RBAC, and ChatGPT Enterprise retention and residency settings

15- With an API key, usage follows your API organization's retention and data-sharing settings instead

17For the CLI, Sign in with ChatGPT is the default authentication path when no valid session is available.

12### Sign in with ChatGPT19### Sign in with ChatGPT

13 20

14When you sign in with ChatGPT from the Codex app, CLI, or IDE Extension, Codex opens a browser window for you to complete the login flow. After you sign in, the browser returns an access token to the CLI or IDE extension.21When you sign in with ChatGPT from the Codex app, CLI, or IDE Extension, Codex opens a browser window for you to complete the login flow. After you sign in, the browser returns an access token to the CLI or IDE extension.

19 26

20OpenAI bills API key usage through your OpenAI Platform account at standard API rates. See the [API pricing page](https://openai.com/api/pricing/).27OpenAI bills API key usage through your OpenAI Platform account at standard API rates. See the [API pricing page](https://openai.com/api/pricing/).

21 28

29Features that rely on ChatGPT credits, such as [fast mode](https://developers.openai.com/codex/speed), are

30available only when you sign in with ChatGPT. If you sign in with an API key,

31Codex uses standard API pricing instead.

33Recommendation is to use API key authentication for programmatic Codex CLI workflows (for example CI/CD jobs). Don't expose Codex execution in untrusted or public environments.

22## Secure your Codex cloud account35## Secure your Codex cloud account

23 36

24Codex cloud interacts directly with your codebase, so it needs stronger security than many other ChatGPT features. Enable multi-factor authentication (MFA).37Codex cloud interacts directly with your codebase, so it needs stronger security than many other ChatGPT features. Enable multi-factor authentication (MFA).

43 56

44Codex caches login details locally in a plaintext file at `~/.codex/auth.json` or in your OS-specific credential store.57Codex caches login details locally in a plaintext file at `~/.codex/auth.json` or in your OS-specific credential store.

45 58

59For sign in with ChatGPT sessions, Codex refreshes tokens automatically during use before they expire, so active sessions usually continue without requiring another browser login.

46## Credential storage61## Credential storage

47 62

48Use `cli_auth_credentials_store` to control where the Codex CLI stores cached credentials:63Use `cli_auth_credentials_store` to control where the Codex CLI stores cached credentials:

74 89

75If the active credentials don't match the configured restrictions, Codex logs the user out and exits.90If the active credentials don't match the configured restrictions, Codex logs the user out and exits.

76 91

~~77These settings are commonly applied via managed configuration rather than per-user setup. See [Managed configuration](https://developers.openai.com/codex/security#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).

78 93

79## Login on headless devices94## Login on headless devices

80 95

130docker cp ~/.codex/auth.json MY_CONTAINER:"$CONTAINER_HOME/.codex/auth.json"145docker cp ~/.codex/auth.json MY_CONTAINER:"$CONTAINER_HOME/.codex/auth.json"

131```146```

132 147

148For a more advanced version of this same pattern on trusted CI/CD runners, see

149[Maintain Codex account auth in CI/CD (advanced)](https://developers.openai.com/codex/auth/ci-cd-auth).

150That guide explains how to let Codex refresh `auth.json` during normal runs and

151then keep the updated file for the next job. API keys are still the recommended

152default for automation.

153

133### Fallback: Forward the localhost callback over SSH154### Fallback: Forward the localhost callback over SSH

134 155

135If you can forward ports between your local machine and the remote host, you can use the standard browser-based flow by tunneling Codex's local callback server (default `localhost:1455`).156If you can forward ports between your local machine and the remote host, you can use the standard browser-based flow by tunneling Codex's local callback server (default `localhost:1455`).

auth/ci-cd-auth.md +277 −0 added

Details

1# Maintain Codex account auth in CI/CD (advanced)

3This guide shows how to keep ChatGPT-managed Codex auth working on a trusted

4CI/CD runner without calling the OAuth token endpoint yourself.

6The right way to authenticate automation is with an API key. Use this guide

7only if you specifically need to run the workflow as your Codex account.

9The pattern is:

111. Create `auth.json` once on a trusted machine with `codex login`.

122. Put that file on the runner.

133. Run Codex normally.

144. Let Codex refresh the session when it becomes stale.

155. Keep the refreshed `auth.json` for the next run.

17This is an advanced workflow for enterprise and other trusted private

18automation. API keys are still the recommended option for most CI/CD jobs.

20Treat `~/.codex/auth.json` like a password: it contains access tokens. Don't

21 commit it, paste it into tickets, or share it in chat. Do not use this

22 workflow for public or open-source repositories.

24## Why this works

26Codex already knows how to refresh a ChatGPT-managed session.

28As of the current open-source client:

30- Codex loads the local auth cache from `auth.json`

31- if `last_refresh` is older than about 8 days, Codex refreshes the token

32 bundle before the run continues

33- after a successful refresh, Codex writes the new tokens and a new

34 `last_refresh` back to `auth.json`

35- if a request gets a `401`, Codex also has a built-in refresh-and-retry path

37That means the supported CI/CD strategy is not "call the refresh API yourself."

38It is "run Codex and persist the updated `auth.json`."

40## When to use this

42Use this guide only when all of the following are true:

44- you need ChatGPT-managed Codex auth rather than an API key

45- `codex login` cannot run on the remote runner

46- the runner is trusted private infrastructure

47- you can preserve the refreshed `auth.json` between runs

48- only one machine or serialized job stream will use a given `auth.json` copy

50This guide applies to Codex-managed ChatGPT auth (`auth_mode: "chatgpt"`).

52It does not apply to:

54- API key auth

55- external-token host integrations (`auth_mode: "chatgptAuthTokens"`)

56- generic OAuth clients outside Codex

58If your credentials are stored in the OS keyring, switch to file-backed storage

59first. See [Credential storage](https://developers.openai.com/codex/auth#credential-storage).

61## Seed `auth.json` once

63On a trusted machine where browser login is possible:

651. Configure Codex to store credentials in a file:

67```toml

68cli_auth_credentials_store = "file"

69```

712. Run:

73```bash

74codex login

75```

773. Verify the file looks like managed ChatGPT auth:

79```bash

80AUTH_FILE="${CODEX_HOME:-$HOME/.codex}/auth.json"

82jq '{

83 auth_mode,

84 has_tokens: (.tokens != null),

85 has_refresh_token: ((.tokens.refresh_token // "") != ""),

86 last_refresh

87}' "$AUTH_FILE"

88```

90Continue only if:

92- `auth_mode` is `"chatgpt"`

93- `has_refresh_token` is `true`

95Then place the contents of `auth.json` into your CI/CD secret manager or copy

96it to a trusted persistent runner.

98## Recommended pattern: GitHub Actions on a self-hosted runner

100The simplest fully automated setup is a self-hosted GitHub Actions runner with a

101persistent `CODEX_HOME`.

102

103Why this pattern works well:

104

105- the runner can keep `auth.json` on disk between jobs

106- Codex can refresh the file in place

107- later jobs automatically pick up the refreshed tokens

108- you only need the original secret for bootstrap or reseeding

109

110The critical detail is to seed `auth.json` only if it is missing. If you

111rewrite the file from the original secret on every run, you throw away the

112refreshed tokens that Codex just wrote.

113

114Example scheduled workflow:

115

116```yaml

117name: Keep Codex auth fresh

118

119on:

120 schedule:

121 - cron: "0 9 * * 1"

122 workflow_dispatch:

123

124jobs:

125 keep-codex-auth-fresh:

126 runs-on: self-hosted

127 steps:

128 - name: Bootstrap auth.json if needed

129 shell: bash

130 env:

131 CODEX_AUTH_JSON: ${{ secrets.CODEX_AUTH_JSON }}

132 run: |

133 export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"

134 mkdir -p "$CODEX_HOME"

135 chmod 700 "$CODEX_HOME"

136

137 if [ ! -f "$CODEX_HOME/auth.json" ]; then

138 printf '%s' "$CODEX_AUTH_JSON" > "$CODEX_HOME/auth.json"

139 chmod 600 "$CODEX_HOME/auth.json"

140 fi

141

142 - name: Run Codex

143 shell: bash

144 run: |

145 codex exec --json "Reply with the single word OK." >/dev/null

146```

147

148What this does:

149

150- the first run seeds `auth.json`

151- later runs reuse the same file

152- once the cached session is old enough, Codex refreshes it during the normal

153 `codex exec` step

154- the refreshed file remains on disk for the next workflow run

155

156A weekly schedule is usually enough because Codex treats the session as stale

157after roughly 8 days in the current open-source client.

158

159## Ephemeral runners: restore, run Codex, persist the updated file

160

161If you use GitHub-hosted runners, GitLab shared runners, or any other ephemeral

162environment, the runner filesystem disappears after each job. In that setup,

163you need a round-trip:

164

1651. restore the current `auth.json` from secure storage

1662. run Codex

1673. write the updated `auth.json` back to secure storage

168

169Generic GitHub Actions shape:

170

171```yaml

172name: Run Codex with managed auth

173

174on:

175 workflow_dispatch:

176

177jobs:

178 codex-job:

179 runs-on: ubuntu-latest

180 steps:

181 - name: Restore auth.json

182 shell: bash

183 run: |

184 export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"

185 mkdir -p "$CODEX_HOME"

186 chmod 700 "$CODEX_HOME"

187

188 # Replace this with your secret manager or secure storage command.

189 my-secret-cli read codex-auth-json > "$CODEX_HOME/auth.json"

190 chmod 600 "$CODEX_HOME/auth.json"

191

192 - name: Run Codex

193 shell: bash

194 run: |

195 codex exec --json "summarize the failing tests"

196

197 - name: Persist refreshed auth.json

198 if: always()

199 shell: bash

200 run: |

201 # Replace this with your secret manager or secure storage command.

202 my-secret-cli write codex-auth-json < "$CODEX_HOME/auth.json"

203```

204

205The key requirement is that the write-back step stores the refreshed file that

206Codex produced during the run, not the original seed.

207

208## You do not need a separate refresh command

209

210Any normal Codex run can refresh the session.

211

212That means you have two good options:

213

214- let your existing CI/CD Codex job refresh the file naturally

215- add a lightweight scheduled maintenance job, like the GitHub Actions example

216 above, if your real jobs do not run often enough

217

218The first Codex run after the session becomes stale is the one that refreshes

219`auth.json`.

220

221## Operational rules that matter

222

223- Use one `auth.json` per runner or per serialized workflow stream.

224- Do not share the same file across concurrent jobs or multiple machines.

225- Do not overwrite a persistent runner's refreshed file from the original seed

226 on every run.

227- Do not store `auth.json` in the repository, logs, or public artifact storage.

228- Reseed from a trusted machine if built-in refresh stops working.

229

230## What to do when refresh stops working

231

232This flow reduces manual work, but it does not guarantee the same session lasts

233forever.

234

235Reseed the runner with a fresh `auth.json` if:

236

237- Codex starts returning `401` and the runner can no longer refresh

238- the refresh token was revoked or expired

239- another machine or concurrent job rotated the token first

240- your secure-storage round trip failed and an old file was restored

241

242To reseed:

243

2441. Run `codex login` on a trusted machine.

2452. Replace the stored CI/CD copy of `auth.json`.

2463. Let the next runner job continue using Codex's built-in refresh flow.

247

248## Verify that the runner is maintaining the session

249

250Check that the runner still has managed auth tokens and that `last_refresh`

251exists:

252

253```bash

254AUTH_FILE="${CODEX_HOME:-$HOME/.codex}/auth.json"

255

256jq '{

257 auth_mode,

258 last_refresh,

259 has_access_token: ((.tokens.access_token // "") != ""),

260 has_id_token: ((.tokens.id_token // "") != ""),

261 has_refresh_token: ((.tokens.refresh_token // "") != "")

262}' "$AUTH_FILE"

263```

264

265If your runner is persistent, you should see the same file continue to exist

266between runs. If your runner is ephemeral, confirm that your write-back step is

267storing the updated file from the last job.

268

269## Source references

270

271If you want to verify this behavior in the open-source client:

272

273- [`codex-rs/core/src/auth.rs`](https://github.com/openai/codex/blob/main/codex-rs/core/src/auth.rs)

274 covers stale-token detection, automatic refresh, refresh-on-401 recovery, and

275 persistence of refreshed tokens

276- [`codex-rs/core/src/auth/storage.rs`](https://github.com/openai/codex/blob/main/codex-rs/core/src/auth/storage.rs)

277 covers file-backed `auth.json` storage

cli.md +1 −1

Details

55 55

56Run `codex` to start an interactive terminal UI (TUI) session.](https://developers.openai.com/codex/cli/features#running-in-interactive-mode)[### Control model and reasoning56Run `codex` to start an interactive terminal UI (TUI) session.](https://developers.openai.com/codex/cli/features#running-in-interactive-mode)[### Control model and reasoning

57 57

~~58Use `/model` to switch between GPT-5.3-Codex and other available models, or adjust reasoning levels.](https://developers.openai.com/codex/cli/features#models-reasoning)[### Image inputs~~58Use `/model` to switch between GPT-5.4, GPT-5.3-Codex, and other available models, or adjust reasoning levels.](https://developers.openai.com/codex/cli/features#models-reasoning)[### Image inputs

59 59

60Attach screenshots or design specs so Codex reads them alongside your prompt.](https://developers.openai.com/codex/cli/features#image-inputs)[### Run local code review60Attach screenshots or design specs so Codex reads them alongside your prompt.](https://developers.openai.com/codex/cli/features#image-inputs)[### Run local code review

61 61

cli/features.md +13 −4

Details

20 20

21- Send prompts, code snippets, or screenshots (see [image inputs](#image-inputs)) directly into the composer.21- Send prompts, code snippets, or screenshots (see [image inputs](#image-inputs)) directly into the composer.

22- Watch Codex explain its plan before making a change, and approve or reject steps inline.22- Watch Codex explain its plan before making a change, and approve or reject steps inline.

23- Read syntax-highlighted markdown code blocks and diffs in the TUI, then use `/theme` to preview and save a preferred color theme.

24- Use `/clear` to wipe the terminal and start a fresh chat, or press <kbd>Ctrl</kbd>+<kbd>L</kbd> to clear the screen without starting a new conversation.

25- Use `/copy` to copy the latest completed Codex output. If a turn is still running, Codex copies the most recent finished output instead of in-progress text.

23- Navigate draft history in the composer with <kbd>Up</kbd>/<kbd>Down</kbd>; Codex restores prior draft text and image placeholders.26- Navigate draft history in the composer with <kbd>Up</kbd>/<kbd>Down</kbd>; Codex restores prior draft text and image placeholders.

24- Press <kbd>Ctrl</kbd>+<kbd>C</kbd> or use `/exit` to close the interactive session when you're done.27- Press <kbd>Ctrl</kbd>+<kbd>C</kbd> or use `/exit` to close the interactive session when you're done.

25 28

43 46

44## Models and reasoning47## Models and reasoning

45 48

46For most coding tasks in Codex, `gpt-5.3-codex` is the go-to model. It’s available for ChatGPT-authenticated Codex sessions in the Codex app, CLI, IDE extension, and Codex Cloud. 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 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.

47 50

~~48Switch models mid-session with the /model command, or specify one when launching the CLI.~~51Switch models mid-session with the `/model` command, or specify one when launching the CLI.

49 52

50```bash53```bash

~~51codex --model gpt-5.3-codex~~54codex --model gpt-5.4

52```55```

53 56

54[Learn more about the models available in Codex](https://developers.openai.com/codex/models).57[Learn more about the models available in Codex](https://developers.openai.com/codex/models).

83 86

84Codex accepts common formats such as PNG and JPEG. Use comma-separated filenames for two or more images, and combine them with text instructions to add context.87Codex accepts common formats such as PNG and JPEG. Use comma-separated filenames for two or more images, and combine them with text instructions to add context.

85 88

89## Syntax highlighting and themes

91The TUI syntax-highlights fenced markdown code blocks and file diffs so code is easier to scan during reviews and debugging.

93Use `/theme` to open the theme picker, preview themes live, and save your selection to `tui.theme` in `~/.codex/config.toml`. You can also add custom `.tmTheme` files under `$CODEX_HOME/themes` and select them in the picker.

86## Running local code review95## Running local code review

87 96

88Type `/review` in the CLI to open Codex's review presets. The CLI launches a dedicated reviewer that reads the diff you select and reports prioritized, actionable findings without touching your working tree. By default it uses the current session model; set `review_model` in `config.toml` to override.97Type `/review` in the CLI to open Codex's review presets. The CLI launches a dedicated reviewer that reads the diff you select and reports prioritized, actionable findings without touching your working tree. By default it uses the current session model; set `review_model` in `config.toml` to override.

96 105

97## Web search106## Web search

98 107

99Codex ships with a first-party web search tool. For local tasks in the Codex CLI, Codex enables web search by default and serves results from a web search cache. The cache is an OpenAI-maintained index of web results, so cached mode returns pre-indexed results instead of fetching live pages. This reduces exposure to prompt injection from arbitrary live content, but you should still treat web results as untrusted. If you are using `--yolo` or another [full access sandbox setting](https://developers.openai.com/codex/security), web search defaults to live results. To fetch the most recent data, pass `--search` for a single run or set `web_search = "live"` in [Config basics](https://developers.openai.com/codex/config-basic). You can also set `web_search = "disabled"` to turn the tool off.108Codex ships with a first-party web search tool. For local tasks in the Codex CLI, Codex enables web search by default and serves results from a web search cache. The cache is an OpenAI-maintained index of web results, so cached mode returns pre-indexed results instead of fetching live pages. This reduces exposure to prompt injection from arbitrary live content, but you should still treat web results as untrusted. If you are using `--yolo` or another [full access sandbox setting](https://developers.openai.com/codex/agent-approvals-security), web search defaults to live results. To fetch the most recent data, pass `--search` for a single run or set `web_search = "live"` in [Config basics](https://developers.openai.com/codex/config-basic). You can also set `web_search = "disabled"` to turn the tool off.

100 109

101You'll see `web_search` items in the transcript or `codex exec --json` output whenever Codex looks something up.110You'll see `web_search` items in the transcript or `codex exec --json` output whenever Codex looks something up.

102 111

cli/slash-commands.md +86 −27

Details

1# Slash commands in Codex CLI1# Slash commands in Codex CLI

2 2

3Slash commands give you fast, keyboard-first control over Codex. Type `/` in the composer to open the slash popup, choose a command, and Codex will perform actions such as switching models, adjusting permissions, or summarizing long conversations without leaving the terminal.3Slash commands give you fast, keyboard-first control over Codex. Type `/` in

4the composer to open the slash popup, choose a command, and Codex will perform

5actions such as switching models, adjusting permissions, or summarizing long

6conversations without leaving the terminal.

4 7

5This guide shows you how to:8This guide shows you how to:

6 9

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

~~8- Steer an active session with commands like `/model`, `/personality`, `/permissions`, `/experimental`, `/agent`, and `/status`~~11- Steer an active session with commands like `/model`, `/personality`,

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

9 13

10## Built-in slash commands14## Built-in slash commands

11 15

~~12Codex ships with the following commands. Open the slash popup and start typing the command name to filter the list.~~16Codex ships with the following commands. Open the slash popup and start typing

17the command name to filter the list.

13 18

15| ------------------------------------------------------------------------------- | --------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |20| ------------------------------------------------------------------------------- | --------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |

17| [`/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. |

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. |

20| [`/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. |

39| [`/debug-config`](#inspect-config-layers-with-debug-config) | Print config layer and requirements diagnostics. | Debug precedence and policy requirements, including experimental network constraints. |46| [`/debug-config`](#inspect-config-layers-with-debug-config) | Print config layer and requirements diagnostics. | Debug precedence and policy requirements, including experimental network constraints. |

40| [`/statusline`](#configure-footer-items-with-statusline) | Configure TUI status-line fields interactively. | Pick and reorder footer items (model/context/limits/git/tokens/session) and persist in config.toml. |47| [`/statusline`](#configure-footer-items-with-statusline) | Configure TUI status-line fields interactively. | Pick and reorder footer items (model/context/limits/git/tokens/session) and persist in config.toml. |

41 48

~~42`/quit` and `/exit` both exit the CLI. Use them only after you have saved or committed any important work.~~49`/quit` and `/exit` both exit the CLI. Use them only after you have saved or

50committed any important work.

43 51

44The `/approvals` command still works as an alias, but it no longer appears in the slash popup list.52The `/approvals` command still works as an alias, but it no longer appears in the slash popup list.

45 53

621. In an active conversation, type `/personality` and press Enter.701. In an active conversation, type `/personality` and press Enter.

632. Choose a style from the popup.712. Choose a style from the popup.

64 72

~~65Expected: Codex confirms the new style in the transcript and uses it for later responses in the thread.~~73Expected: Codex confirms the new style in the transcript and uses it for later

74responses in the thread.

66 75

~~67Codex supports `friendly`, `pragmatic`, and `none` personalities. Use `none` to disable personality instructions.~~76Codex supports `friendly`, `pragmatic`, and `none` personalities. Use `none`

77to disable personality instructions.

68 78

69If the active model doesn't support personality-specific instructions, Codex hides this command.79If the active model doesn't support personality-specific instructions, Codex hides this command.

70 80

71### Switch to plan mode with `/plan`81### Switch to plan mode with `/plan`

72 82

~~731. Type `/plan` and press Enter to switch the active conversation into plan mode.~~831. Type `/plan` and press Enter to switch the active conversation into plan

84 mode.

742. Optional: provide inline prompt text (for example, `/plan Propose a migration plan for this service`).852. Optional: provide inline prompt text (for example, `/plan Propose a migration plan for this service`).

753. You can paste content or attach images while using inline `/plan` arguments.863. You can paste content or attach images while using inline `/plan` arguments.

76 87

85 96

86Expected: Codex saves your feature choices to config and applies them on restart.97Expected: Codex saves your feature choices to config and applies them on restart.

87 98

99### Clear the terminal and start a new chat with `/clear`

100

1011. Type `/clear` and press Enter.

102

103Expected: Codex clears the terminal, resets the visible transcript, and starts

104a fresh chat in the same CLI session.

105

106Unlike <kbd>Ctrl</kbd>+<kbd>L</kbd>, `/clear` starts a new conversation.

107

108<kbd>Ctrl</kbd>+<kbd>L</kbd> only clears the terminal view and keeps the current

109chat. Codex disables both actions while a task is in progress.

110

88### Update permissions with `/permissions`111### Update permissions with `/permissions`

89 112

901. Type `/permissions` and press Enter.1131. Type `/permissions` and press Enter.

~~912. Select the approval preset that matches your comfort level, for example `Auto` for hands-off runs or `Read Only` to review edits.~~1142. Select the approval preset that matches your comfort level, for example

115 `Auto` for hands-off runs or `Read Only` to review edits.

92 116

~~93Expected: Codex announces the updated policy. Future actions respect the new approval mode until you change it again.~~117Expected: Codex announces the updated policy. Future actions respect the

118updated approval mode until you change it again.

119

120### Copy the latest response with `/copy`

121

1221. Type `/copy` and press Enter.

123

124Expected: Codex copies the latest completed Codex output to your clipboard.

125

126If a turn is still running, `/copy` uses the latest completed output instead of

127the in-progress response. The command is unavailable before the first completed

128Codex output and immediately after a rollback.

94 129

95### Grant sandbox read access with `/sandbox-add-read-dir`130### Grant sandbox read access with `/sandbox-add-read-dir`

96 131

991. Type `/sandbox-add-read-dir C:\absolute\directory\path` and press Enter.1341. Type `/sandbox-add-read-dir C:\absolute\directory\path` and press Enter.

1002. Confirm the path is an existing absolute directory.1352. Confirm the path is an existing absolute directory.

101 136

102Expected: Codex refreshes the Windows sandbox policy and grants read access to that directory for later commands that run in the sandbox.137Expected: Codex refreshes the Windows sandbox policy and grants read access to

138that directory for later commands that run in the sandbox.

103 139

104### Inspect the session with `/status`140### Inspect the session with `/status`

105 141

1061. In any conversation, type `/status`.1421. In any conversation, type `/status`.

1072. Review the output for the active model, approval policy, writable roots, and current token usage.1432. Review the output for the active model, approval policy, writable roots, and current token usage.

108 144

109Expected: You see a summary like what `codex status` prints in the shell, confirming Codex is operating where you expect.145Expected: You see a summary like what `codex status` prints in the shell,

146confirming Codex is operating where you expect.

110 147

111### Inspect config layers with `/debug-config`148### Inspect config layers with `/debug-config`

112 149

1131. Type `/debug-config`.1501. Type `/debug-config`.

1142. Review the output for config layer order (lowest precedence first), on/off state, and policy sources.1512. Review the output for config layer order (lowest precedence first), on/off

152 state, and policy sources.

115 153

116Expected: Codex prints layer diagnostics plus policy details such as `allowed_approval_policies`, `allowed_sandbox_modes`, `mcp_servers`, `rules`, `enforce_residency`, and `experimental_network` when configured.154Expected: Codex prints layer diagnostics plus policy details such as

155`allowed_approval_policies`, `allowed_sandbox_modes`, `mcp_servers`, `rules`,

156`enforce_residency`, and `experimental_network` when configured.

117 157

118Use this output to debug why an effective setting differs from `config.toml`.158Use this output to debug why an effective setting differs from `config.toml`.

119 159

1221. Type `/statusline`.1621. Type `/statusline`.

1232. Use the picker to toggle and reorder items, then confirm.1632. Use the picker to toggle and reorder items, then confirm.

124 164

125Expected: The footer status line updates immediately and persists to `tui.status_line` in `config.toml`.165Expected: The footer status line updates immediately and persists to

166`tui.status_line` in `config.toml`.

126 167

127Available status-line items include model, model+reasoning, context stats, rate limits, git branch, token counters, session id, current directory/project root, and Codex version.168Available status-line items include model, model+reasoning, context stats, rate

169limits, git branch, token counters, session id, current directory/project root,

170and Codex version.

128 171

129### Check background terminals with `/ps`172### Check background terminals with `/ps`

130 173

1311. Type `/ps`.1741. Type `/ps`.

1322. Review the list of background terminals and their status.1752. Review the list of background terminals and their status.

133 176

134Expected: Codex shows each background terminal’s command plus up to three recent, non-empty output lines so you can gauge progress at a glance.177Expected: Codex shows each background terminal's command plus up to three

178recent, non-empty output lines so you can gauge progress at a glance.

135 179

136Background terminals appear when `unified_exec` is in use; otherwise, the list may be empty.180Background terminals appear when `unified_exec` is in use; otherwise, the list may be empty.

137 181

1401. After a long exchange, type `/compact`.1841. After a long exchange, type `/compact`.

1412. Confirm when Codex offers to summarize the conversation so far.1852. Confirm when Codex offers to summarize the conversation so far.

142 186

143Expected: Codex replaces earlier turns with a concise summary, freeing context while keeping critical details.187Expected: Codex replaces earlier turns with a concise summary, freeing context

188while keeping critical details.

144 189

145### Review changes with `/diff`190### Review changes with `/diff`

146 191

1471. Type `/diff` to inspect the Git diff.1921. Type `/diff` to inspect the Git diff.

1482. Scroll through the output inside the CLI to review edits and added files.1932. Scroll through the output inside the CLI to review edits and added files.

149 194

150Expected: Codex shows changes you’ve staged, changes you haven’t staged yet, and files Git hasn’t started tracking, so you can decide what to keep.195Expected: Codex shows changes you've staged, changes you haven't staged yet,

196and files Git hasn't started tracking, so you can decide what to keep.

151 197

152### Highlight files with `/mention`198### Highlight files with `/mention`

153 199

160 206

1611. Type `/new` and press Enter.2071. Type `/new` and press Enter.

162 208

163Expected: Codex starts a fresh conversation in the same CLI session, so you can switch tasks without leaving your terminal.209Expected: Codex starts a fresh conversation in the same CLI session, so you

210can switch tasks without leaving your terminal.

211

212Unlike `/clear`, `/new` does not clear the current terminal view first.

164 213

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

166 215

1671. Type `/resume` and press Enter.2161. Type `/resume` and press Enter.

1682. Choose the session you want from the saved-session picker.2172. Choose the session you want from the saved-session picker.

169 218

170Expected: Codex reloads the selected conversation’s transcript so you can pick up where you left off, keeping the original history intact.219Expected: Codex reloads the selected conversation's transcript so you can pick

220up where you left off, keeping the original history intact.

171 221

172### Fork the current conversation with `/fork`222### Fork the current conversation with `/fork`

173 223

1741. Type `/fork` and press Enter.2241. Type `/fork` and press Enter.

175 225

176Expected: Codex clones the current conversation into a new thread with a fresh ID, leaving the original transcript untouched so you can explore an alternative approach in parallel.226Expected: Codex clones the current conversation into a new thread with a fresh

227ID, leaving the original transcript untouched so you can explore an alternative

228approach in parallel.

177 229

178If you need to fork a saved session instead of the current one, run `codex fork` in your terminal to open the session picker.230If you need to fork a saved session instead of the current one, run

231`codex fork` in your terminal to open the session picker.

179 232

180### Generate `AGENTS.md` with `/init`233### Generate `AGENTS.md` with `/init`

181 234

1821. Run `/init` in the directory where you want Codex to look for persistent instructions.2351. Run `/init` in the directory where you want Codex to look for persistent instructions.

1832. Review the generated `AGENTS.md`, then edit it to match your repository conventions.2362. Review the generated `AGENTS.md`, then edit it to match your repository conventions.

184 237

185Expected: Codex creates an `AGENTS.md` scaffold you can refine and commit for future sessions.238Expected: Codex creates an `AGENTS.md` scaffold you can refine and commit for

239future sessions.

186 240

187### Ask for a working tree review with `/review`241### Ask for a working tree review with `/review`

188 242

1891. Type `/review`.2431. Type `/review`.

1902. Follow up with `/diff` if you want to inspect the exact file changes.2442. Follow up with `/diff` if you want to inspect the exact file changes.

191 245

192Expected: Codex summarizes issues it finds in your working tree, focusing on behavior changes and missing tests. It uses the current session model unless you set `review_model` in `config.toml`.246Expected: Codex summarizes issues it finds in your working tree, focusing on

247behavior changes and missing tests. It uses the current session model unless

248you set `review_model` in `config.toml`.

193 249

194### List MCP tools with `/mcp`250### List MCP tools with `/mcp`

195 251

2031. Type `/apps`.2591. Type `/apps`.

2042. Pick an app from the list.2602. Pick an app from the list.

205 261

206Expected: Codex inserts the app mention into the composer as `$app-slug`, so you can immediately ask Codex to use it.262Expected: Codex inserts the app mention into the composer as `$app-slug`, so

263you can immediately ask Codex to use it.

207 264

208### Switch agent threads with `/agent`265### Switch agent threads with `/agent`

209 266

2101. Type `/agent` and press Enter.2671. Type `/agent` and press Enter.

2112. Select the thread you want from the picker.2682. Select the thread you want from the picker.

212 269

213Expected: Codex switches the active thread so you can inspect or continue that agent’s work.270Expected: Codex switches the active thread so you can inspect or continue that

271agent's work.

214 272

215### Send feedback with `/feedback`273### Send feedback with `/feedback`

216 274

2171. Type `/feedback` and press Enter.2751. Type `/feedback` and press Enter.

2182. Follow the prompts to include logs or diagnostics.2762. Follow the prompts to include logs or diagnostics.

219 277

220Expected: Codex collects the requested diagnostics and submits them to the maintainers.278Expected: Codex collects the requested diagnostics and submits them to the

279maintainers.

221 280

222### Sign out with `/logout`281### Sign out with `/logout`

223 282

codex.md +6 −2

Details

22 22

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

24 24

~~25Join the OpenAI Discord to ask questions, share workflows and connect with others.~~25Explore Codex Ambassadors and upcoming community meetups by location.

26 26

~~27 Join the Discord](https://discord.gg/openai)~~27 See community](https://developers.openai.com/codex/community/meetups) [### Codex for OSS

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

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

codex-for-oss-terms.md +47 −0 added

Details

1# Codex for Open Source Program Terms

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.

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.

7## 1. Program Overview

9The Program is designed to support maintainers of important open-source software. Approved applicants may receive one or more of the following benefits, as determined by OpenAI in its sole discretion: (i) a limited-duration ChatGPT Pro benefit that includes Codex access; (ii) API credits for eligible open-source maintainer workflows; and (iii) conditional access to Codex Security for qualified repositories or maintainers. Availability, duration, scope, and timing of any benefit may vary by applicant, repository, or use case.

11## 2. Eligibility and Applications

13To be considered for the Program, applicants must have a valid ChatGPT account and provide accurate and complete information about themselves, their repositories, and their role in maintaining or administering those repositories. OpenAI may consider factors such as repository usage, ecosystem importance, evidence of active maintenance, role or permissions, and Program capacity. Submission of an application does not guarantee selection, funding, or access.

15## 3. Selection and Verification

17OpenAI may approve or deny applications in its sole discretion. OpenAI may request additional information to verify identity, repository affiliation, maintainer status, or repository control, and may condition any benefit on successful verification. OpenAI's decisions are final.

19## 4. Benefits

21Unless OpenAI states otherwise in writing, Program benefits are personal, limited, non-transferable, and have no cash value. Program benefits may not be sold, assigned, sublicensed, exchanged, or shared. If OpenAI provides a redemption code, invitation, or activation flow, the recipient must follow the applicable redemption instructions and any additional redemption terms communicated by OpenAI. Benefits may expire if they are not redeemed or activated within the period specified by OpenAI.

23## 5. Additional Conditions for Codex Security and API Credits

25Codex Security access and API credits are optional, additional Program benefits and may require separate review, additional eligibility checks, and/or additional terms. OpenAI may limit Codex Security access to repositories that the applicant owns, maintains, or is otherwise authorized to administer.

27Applicants may not use the Program, including Codex Security, to scan, probe, test, or review repositories, systems, or codebases that they do not own or lack permission to review. OpenAI may require proof of control or authorization before granting or continuing such access and may limit or revoke access at any time if authorization is unclear or no longer valid.

29## 6. Fraud, Abuse, and Revocation

31OpenAI may reject, suspend, or revoke any Program benefit for any reason in its sole discretion, including without limitation if it reasonably believes that an applicant or recipient: (i) provided false, misleading, or incomplete information; (ii) used multiple identities or accounts to obtain more than one benefit; (iii) transferred, resold, or shared a benefit; (iv) violated OpenAI's terms or policies; (v) used the Program in a harmful, abusive, fraudulent, or unauthorized manner; or (vi) otherwise created legal, security, reputational, or operational risk for OpenAI or others.

33## 7. Submission Similarity; No Exclusivity; No Confidentiality

35The applicant acknowledges that OpenAI may currently or in the future develop, receive, review, fund, support, or work with ideas, projects, repositories, workflows, or proposals that are similar or identical to the applicant's submission. Nothing in these Program Terms prevents OpenAI from independently developing, funding, or supporting any such similar or identical work.

37The applicant further acknowledges that OpenAI assumes no obligation of exclusivity with respect to any submission and that any decision to select, fund, or support a project or maintainer is made in OpenAI's sole discretion.

39Except as described in OpenAI's privacy policy or as required by law, applicants should not submit confidential information in connection with the Program, and OpenAI has no duty to treat application materials as confidential.

41## 8. Program Changes

43OpenAI may modify, pause, limit, or discontinue the Program, its eligibility criteria, or any Program benefit at any time. OpenAI may also update these Program Terms from time to time. Continued participation in the Program after an update constitutes acceptance of the revised Program Terms.

45## 9. Taxes and Local Restrictions

47Recipients are responsible for any taxes, reporting obligations, or local legal requirements that may apply to receipt or use of Program benefits. The Program is void where prohibited or restricted by law.

community/codex-for-oss.md +19 −0 added

Details

1# Codex for Open Source

3Open-source maintainers do critical work, often behind the scenes, to keep the software ecosystem healthy. Over the past year, the Codex Open Source Fund ($1 million) has supported projects that need API credits, including teams using Codex to power GitHub pull request workflows. OpenAI is grateful to the maintainers who keep that work moving.

5The fund now supports eligible maintainers by offering six months of ChatGPT Pro with Codex and conditional access to Codex Security for core maintainers with write access. Developers should code in the tools they prefer, whether that’s Codex, [OpenCode](https://github.com/anomalyco/opencode), [Cline](https://github.com/cline/cline), [pi](https://github.com/badlogic/pi-mono/tree/main/packages/coding-agent), [OpenClaw](https://github.com/openclaw/openclaw), or something else, and this program supports that work.

7## What the program includes

9- Six months of ChatGPT Pro with Codex for day-to-day coding, triage, review, and maintainer workflows

10- Conditional access to Codex Security for repositories that need deeper security coverage

11- API credits through the Codex Open Source Fund for projects that use Codex in pull request review, maintainer automation, release workflows, or other core OSS work

13Given GPT-5.4’s capabilities, the team reviews Codex Security access case by case to ensure these workflows get the care and diligence they require.

15If you’re a core maintainer or run a widely used public project, apply. If your project doesn’t fit the criteria but it plays an important role in the ecosystem, apply anyway and explain why.

17By submitting an application, you agree to the [Codex for Open Source Program Terms](https://developers.openai.com/codex/codex-for-oss-terms).

19[Apply today!](https://openai.com/form/codex-for-oss/)

community/meetups.md +17 −0 added

Details

1# Codex Meetups

3Mar 12

5![Stylized city cover for Orlando](https://developers.openai.com/codex/meetups/orlando.webp)

7UpcomingMar 12

9Orlando, FL, USA

11### Orlando

13March 12, 2026

15Hosted by [Leonard](https://www.linkedin.com/in/lgofman/), [Michael](https://www.linkedin.com/in/michael-rusudev/), and [Carlos](https://www.linkedin.com/in/cataladev/)

17[Register now](https://luma.com/39y2dvwx)[Share city](https://developers.openai.com/codex/community/meetups?city=Orlando)

concepts/customization.md +150 −0 added

Details

1# Customization

3Customization is how you make Codex work the way your team works.

5In Codex, customization comes from a few layers that work together:

7- **Project guidance (`AGENTS.md`)** for persistent instructions

8- **Skills** for reusable workflows and domain expertise

9- **[MCP](https://developers.openai.com/codex/mcp)** for access to external tools and shared systems

10- **[Multi-agents](https://developers.openai.com/codex/concepts/multi-agents)** for delegating work to specialized sub-agents

12These are complementary, not competing. `AGENTS.md` shapes behavior, skills package repeatable processes, and [MCP](https://developers.openai.com/codex/mcp) connects Codex to systems outside the local workspace.

14## AGENTS Guidance

16`AGENTS.md` gives Codex durable project guidance that travels with your repository and applies before the agent starts work. Keep it small.

18Use it for the rules you want Codex to follow every time in a repo, such as:

20- Build and test commands

21- Review expectations

22- Repo-specific conventions

23- Directory-specific instructions

25When the agent makes incorrect assumptions about your codebase, correct them in `AGENTS.md` and ask the agent to update `AGENTS.md` so the fix persists. Treat it as a feedback loop.

27**Updating `AGENTS.md`:** Start with only the instructions that matter. Codify recurring review feedback, put guidance in the closest directory where it applies, and tell the agent to update `AGENTS.md` when you correct something so future sessions inherit the fix.

29### When to update `AGENTS.md`

31- **Repeated mistakes**: If the agent makes the same mistake repeatedly, add a rule.

32- **Too much reading**: If it finds the right files but reads too many documents, add routing guidance (which directories/files to prioritize).

33- **Recurring PR feedback**: If you leave the same feedback more than once, codify it.

34- **In GitHub**: In a pull request comment, tag `@codex` with a request (for example, `@codex add this to AGENTS.md`) to delegate the update to a cloud task.

35- **Automate drift checks**: Use [automations](https://developers.openai.com/codex/app/automations) to run recurring checks (for example, daily) that look for guidance gaps and suggest what to add to `AGENTS.md`.

37Pair `AGENTS.md` with infrastructure that enforces those rules: pre-commit hooks, linters, and type checkers catch issues before you see them, so the system gets smarter about preventing recurring mistakes.

39Codex can load guidance from multiple locations: a global file in your Codex home directory (for you as a developer) and repo-specific files that teams can check in. Files closer to the working directory take precedence.

40Use the global file to shape how Codex communicates with you (for example, review style, verbosity, and defaults), and keep repo files focused on team and codebase rules.

42- ~/.codex/

44 - AGENTS.md Global (for you as a developer)

45- repo-root/

47 - AGENTS.md Repo-specific (for your team)

49[Custom instructions with AGENTS.md](https://developers.openai.com/codex/guides/agents-md)

51## Skills

53Skills give Codex reusable capabilities for repeatable workflows.

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.

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

59- my-skill/

61 - SKILL.md Required: instructions + metadata

62 - scripts/ Optional: executable code

63 - references/ Optional: documentation

64 - assets/ Optional: templates, resources

66The skill directory can include a `scripts/` folder with CLI scripts that Codex invokes as part of the workflow (for example, seed data or run validations). When the workflow needs external systems (issue trackers, design tools, docs servers), pair the skill with [MCP](https://developers.openai.com/codex/mcp).

68Example `SKILL.md`:

70```md

71---

72name: commit

73description: Stage and commit changes in semantic groups. Use when the user wants to commit, organize commits, or clean up a branch before pushing.

74---

761. Do not run `git add .`. Stage files in logical groups by purpose.

772. Group into separate commits: feat → test → docs → refactor → chore.

783. Write concise commit messages that match the change scope.

794. Keep each commit focused and reviewable.

80```

82Use skills for:

84- Repeatable workflows (release steps, review routines, docs updates)

85- Team-specific expertise

86- Procedures that need examples, references, or helper scripts

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.

90| Layer | Global | Repo |

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

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

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

95Codex uses progressive disclosure for skills:

97- It starts with metadata (`name`, `description`) for discovery

98- It loads `SKILL.md` only when a skill is chosen

99- It reads references or runs scripts only when needed

100

101Skills can be invoked explicitly, and Codex can also choose them implicitly when the task matches the skill description. Clear skill descriptions improve triggering reliability.

102

103[Agent Skills](https://developers.openai.com/codex/skills)

104

105## MCP

106

107MCP (Model Context Protocol) is the standard way to connect Codex to external tools and context providers.

108It’s especially useful for remotely hosted systems such as Figma, Linear, Jira, GitHub, or internal knowledge services your team depends on.

109

110Use MCP when Codex needs capabilities that live outside the local repo, such as issue trackers, design tools, browsers, or shared documentation systems.

111

112A useful mental model:

113

114- **Host**: Codex

115- **Client**: the MCP connection inside Codex

116- **Server**: the external tool or context provider

117

118MCP servers can expose:

119

120- **Tools** (actions)

121- **Resources** (readable data)

122- **Prompts** (reusable prompt templates)

123

124This separation helps you reason about trust and capability boundaries. Some servers mainly provide context, while others expose powerful actions.

125

126In practice, MCP is often most useful when paired with skills:

127

128- A skill defines the workflow and names the MCP tools to use

129

130[Model Context Protocol](https://developers.openai.com/codex/mcp)

131

132## Multi-agents

133

134You can create different agents with different roles and prompt them to use tools differently. For example, one agent might run specific testing commands and configurations, while another has MCP servers that fetch production logs for debugging. Each sub-agent stays focused and uses the right tools for its job.

135

136[Multi-agents concepts](https://developers.openai.com/codex/concepts/multi-agents)

137

138## Skills + MCP together

139

140Skills plus MCP is where it all comes together: skills define repeatable workflows, and MCP connects them to external tools and systems.

141If a skill depends on MCP, declare that dependency in `agents/openai.yaml` so Codex can install and wire it automatically (see [Agent Skills](https://developers.openai.com/codex/skills)).

142

143## Next step

144

145Build in this order:

146

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.

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.

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

1504. [Multi-agents](https://developers.openai.com/codex/multi-agent) when you’re ready to delegate noisy or specialized tasks to sub-agents.

concepts/multi-agents.md +53 −0 added

Details

1# Multi-agents

3Codex can run multi-agent workflows by spawning specialized agents in parallel and collecting their results in one response.

5This page explains the core concepts and tradeoffs. For setup, agent configuration, and examples, see [Multi-agents](https://developers.openai.com/codex/multi-agent).

7## Why multi-agent workflows help

9Even with large context windows, models have limits. If you flood the main conversation (where you’re defining requirements, constraints, and decisions) with noisy intermediate output such as exploration notes, test logs, stack traces, and command output, the session can become less reliable over time.

11This is often described as:

13- **Context pollution**: useful information gets buried under noisy intermediate output.

14- **Context rot**: performance degrades as the conversation fills up with less relevant details.

16For background, see Chroma’s writeup on [context rot](https://research.trychroma.com/context-rot).

18Multi-agent workflows help by moving noisy work off the main thread:

20- Keep the **main agent** focused on requirements, decisions, and final outputs.

21- Run specialized **sub-agents** in parallel for exploration, tests, or log analysis.

22- Return **summaries** from sub-agents instead of raw intermediate output.

24As a starting point, use parallel agents for tasks that mostly read (exploration, tests, triage, and summarization). Be more careful with parallel write-heavy workflows, because multiple agents editing code at once can create conflicts and increase coordination overhead.

26## Core terms

28Codex uses a few related terms in multi-agent workflows:

30- **Multi-agent**: A workflow where Codex runs multiple agents in parallel and combines their results.

31- **Sub-agent**: A delegated agent that Codex starts to handle a specific task.

32- **Agent thread**: The CLI thread for an agent, which you can inspect and switch between with `/agent`.

34## Choosing models and reasoning

36Different agents benefit from different model and reasoning settings.

38`gpt-5.3-codex-spark` is available in research preview for ChatGPT Pro

39subscribers. See [Models](https://developers.openai.com/codex/models) for current availability. If you’re

40using Codex via the API, use GPT-5.2-Codex today.

42### Model choice

44- **`gpt-5.3-codex`**: Use for agents that need stronger reasoning, such as code review, security analysis, multi-step implementation, or tasks with ambiguous requirements. The main agent and agents that propose or apply edits usually fit here.

45- **`gpt-5.3-codex-spark`**: Use for agents that prioritize speed over depth, such as exploration, read-heavy scans, or quick summarization tasks. Spark works well for parallel workers that return distilled results to the main agent.

47### Reasoning effort (`model_reasoning_effort`)

49- **`high`**: Use when an agent needs to trace complex logic, validate assumptions, or work through edge cases (for example, reviewer or security-focused agents).

50- **`medium`**: A balanced default for most agents.

51- **`low`**: Use when the task is straightforward and speed matters most.

53Higher reasoning effort increases response time and token usage, but it can improve quality for complex work. For details, see [Models](https://developers.openai.com/codex/models), [Config basics](https://developers.openai.com/codex/config-basic), and [Configuration Reference](https://developers.openai.com/codex/config-reference).

concepts/sandboxing.md +102 −0 added

Details

1# Sandboxing – Codex

3Sandboxing is the boundary that lets Codex act autonomously without giving it

4unrestricted access to your machine. When Codex runs local commands in the

5**Codex app**, **IDE extension**, or **CLI**, those commands run inside a

6constrained environment instead of running with full access by default.

8That environment defines what Codex can do on its own, such as which files it

9can modify and whether commands can use the network. When a task stays inside

10those boundaries, Codex can keep moving without stopping for confirmation. When

11it needs to go beyond them, Codex falls back to the approval flow.

13Sandboxing and approvals are different controls that work together. The

14 sandbox defines technical boundaries. The approval policy decides when Codex

15 must stop and ask before crossing them.

17## What the sandbox does

19The sandbox applies to spawned commands, not just to Codex's built-in file

20operations. If Codex runs tools like `git`, package managers, or test runners,

21those commands inherit the same sandbox boundaries.

23Codex uses platform-native enforcement on each OS. The implementation differs

24between macOS, Linux, WSL, and native Windows, but the idea is the same across

25surfaces: give the agent a bounded place to work so routine tasks can run

26autonomously inside clear limits.

28## Why it matters

30Sandboxing reduces approval fatigue. Instead of asking you to confirm every

31low-risk command, Codex can read files, make edits, and run routine project

32commands within the boundary you already approved.

34It also gives you a clearer trust model for agentic work. You are not just

35trusting the agent's intentions; you are trusting that the agent is operating

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

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

39## How you control it

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

43In the Codex app and IDE, you choose a mode from the permissions selector under

44the composer or chat input. That selector lets you rely on Codex's default

45permissions, switch to full access, or use your custom configuration.

47![Codex app permissions selector showing Default permissions, Full access, and Custom (config.toml)](/images/codex/app/permissions-selector-light.webp)

49In the CLI, use [`/permissions`](https://developers.openai.com/codex/cli/slash-commands#update-permissions-with-permissions)

50to switch modes during a session.

52## Configure defaults

54If you want Codex to start with the same behavior every time, use a custom

55configuration. Codex stores those defaults in `config.toml`, its local settings

56file. [Config basics](https://developers.openai.com/codex/config-basic) explains how it works, and the

57[Configuration reference](https://developers.openai.com/codex/config-reference) documents the exact keys for

58`sandbox_mode`, `approval_policy`, and

59`sandbox_workspace_write.writable_roots`. Use those settings to decide how much

60autonomy Codex gets by default, which directories it can write to, and when it

61should pause for approval.

63At a high level, the common sandbox modes are:

65- `read-only`: Codex can inspect files, but it cannot edit files or run

66 commands without approval.

67- `workspace-write`: Codex can read files, edit within the workspace, and run

68 routine local commands inside that boundary. This is the default low-friction

69 mode for local work.

70- `danger-full-access`: Codex runs without sandbox restrictions. This removes

71 the filesystem and network boundaries and should be used only when you want

72 Codex to act with full access.

74The common approval policies are:

76- `untrusted`: Codex asks before running commands that are not in its trusted

77 set.

78- `on-request`: Codex works inside the sandbox by default and asks when it

79 needs to go beyond that boundary.

80- `never`: Codex does not stop for approval prompts.

82Full access means using `sandbox_mode = "danger-full-access"` together with

83`approval_policy = "never"`. By contrast, `--full-auto` is the lower-risk local

84automation preset: `sandbox_mode = "workspace-write"` and

85`approval_policy = "on-request"`.

87If you need Codex to work across more than one directory, writable roots let

88you extend the places it can modify without removing the sandbox entirely. If

89you need a broader or narrower trust boundary, adjust the default sandbox mode

90and approval policy instead of relying on ad hoc exceptions.

92When a workflow needs a specific exception, use [rules](https://developers.openai.com/codex/rules). Rules

93let you allow, prompt, or forbid command prefixes outside the sandbox, which is

94often a better fit than broadly expanding access. For a higher-level overview

95of approvals and sandbox behavior in the app, see

96[Codex app features](https://developers.openai.com/codex/app/features#approvals-and-sandboxing), and for the

97IDE-specific settings entry points, see [Codex IDE extension settings](https://developers.openai.com/codex/ide/settings).

99Platform details live in the platform-specific docs. For native Windows setup,

100behavior, and troubleshooting, see [Windows](https://developers.openai.com/codex/windows). For admin

101requirements and organization-level constraints on sandboxing and approvals, see

102[Agent approvals & security](https://developers.openai.com/codex/agent-approvals-security).

config-advanced.md +18 −5

Details

2 2

3Use these options when you need more control over providers, policies, and integrations. For a quick start, see [Config basics](https://developers.openai.com/codex/config-basic).3Use these options when you need more control over providers, policies, and integrations. For a quick start, see [Config basics](https://developers.openai.com/codex/config-basic).

4 4

5For background on project guidance, reusable capabilities, custom slash commands, multi-agent workflows, and integrations, see [Customization](https://developers.openai.com/codex/concepts/customization). For configuration keys, see [Configuration Reference](https://developers.openai.com/codex/config-reference).

5## Profiles7## Profiles

6 8

7Profiles let you save named sets of configuration values and switch between them from the CLI.9Profiles let you save named sets of configuration values and switch between them from the CLI.

15```toml17```toml

16model = "gpt-5-codex"18model = "gpt-5-codex"

17approval_policy = "on-request"19approval_policy = "on-request"

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

18 21

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

20model = "gpt-5-pro"23model = "gpt-5-pro"

21model_reasoning_effort = "high"24model_reasoning_effort = "high"

22approval_policy = "never"25approval_policy = "never"

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

23 27

24[profiles.lightweight]28[profiles.lightweight]

25model = "gpt-4.1"29model = "gpt-4.1"

28 32

29To make a profile the default, add `profile = "deep-review"` at the top level of `config.toml`. Codex loads that profile unless you override it on the command line.33To make a profile the default, add `profile = "deep-review"` at the top level of `config.toml`. Codex loads that profile unless you override it on the command line.

30 34

35Profiles can also override `model_catalog_json`. When both the top level and the selected profile set `model_catalog_json`, Codex prefers the profile value.

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

32 38

33In addition to editing `~/.codex/config.toml`, you can override configuration for a single run from the CLI:39In addition to editing `~/.codex/config.toml`, you can override configuration for a single run from the CLI:

39 45

40```shell46```shell

41# Dedicated flag47# Dedicated flag

~~42codex --model gpt-5.2~~48codex --model gpt-5.4

43 49

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

~~45codex --config model='"gpt-5.2"'~~51codex --config model='"gpt-5.4"'

46codex --config sandbox_workspace_write.network_access=true52codex --config sandbox_workspace_write.network_access=true

47codex --config 'shell_environment_policy.include_only=["PATH","HOME"]'53codex --config 'shell_environment_policy.include_only=["PATH","HOME"]'

48```54```

182 188

183## Approval policies and sandbox modes189## Approval policies and sandbox modes

184 190

185Pick approval strictness (affects when Codex pauses) and sandbox level (affects file/network access). See [Sandbox & approvals](https://developers.openai.com/codex/security) for deeper examples.191Pick approval strictness (affects when Codex pauses) and sandbox level (affects file/network access).

192

193For operational details that are easy to miss 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

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.

186 196

187```197```

188approval_policy = "untrusted" # Other options: on-request, never198approval_policy = "untrusted" # Other options: on-request, never, or { reject = { ... } }

189sandbox_mode = "workspace-write"199sandbox_mode = "workspace-write"

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

190 201

191[sandbox_workspace_write]202[sandbox_workspace_write]

192exclude_tmpdir_env_var = false # Allow $TMPDIR203exclude_tmpdir_env_var = false # Allow $TMPDIR

195network_access = false # Opt in to outbound network206network_access = false # Opt in to outbound network

196```207```

197 208

209Need the complete key list (including profile-scoped overrides and requirements constraints)? See [Configuration Reference](https://developers.openai.com/codex/config-reference) and [Managed configuration](https://developers.openai.com/codex/enterprise/managed-configuration).

210

198In workspace-write mode, some environments keep `.git/` and `.codex/`211In workspace-write mode, some environments keep `.git/` and `.codex/`

199 read-only even when the rest of the workspace is writable. This is why212 read-only even when the rest of the workspace is writable. This is why

200 commands like `git commit` may still require approval to run outside the213 commands like `git commit` may still require approval to run outside the

291 304

292For more security and privacy guidance around telemetry, see [Security](https://developers.openai.com/codex/security#monitoring-and-telemetry).305For more security and privacy guidance around telemetry, see [Security](https://developers.openai.com/codex/agent-approvals-security#monitoring-and-telemetry).

293 306

294### Metrics307### Metrics

295 308

config-basic.md +20 −7

Details

11The CLI and IDE extension share the same configuration layers. You can use them to:11The CLI and IDE extension share the same configuration layers. You can use them to:

12 12

13- Set the default model and provider.13- Set the default model and provider.

~~14- Configure [approval policies and sandbox settings](https://developers.openai.com/codex/security).~~14- Configure [approval policies and sandbox settings](https://developers.openai.com/codex/agent-approvals-security#sandbox-and-approvals).

15- Configure [MCP servers](https://developers.openai.com/codex/mcp).15- Configure [MCP servers](https://developers.openai.com/codex/mcp).

16 16

17## Configuration precedence17## Configuration precedence

33 33

34On managed machines, your organization may also enforce constraints via34On managed machines, your organization may also enforce constraints via

35 `requirements.toml` (for example, disallowing `approval_policy = "never"` or35 `requirements.toml` (for example, disallowing `approval_policy = "never"` or

~~36`sandbox_mode = "danger-full-access"`). See [Security](https://developers.openai.com/codex/security).~~36 `sandbox_mode = "danger-full-access"`). See [Managed

37 configuration](https://developers.openai.com/codex/enterprise/managed-configuration) and [Admin-enforced

38 requirements](https://developers.openai.com/codex/enterprise/managed-configuration#admin-enforced-requirements-requirementstoml).

37 39

38## Common configuration options40## Common configuration options

39 41

44Choose the model Codex uses by default in the CLI and IDE.46Choose the model Codex uses by default in the CLI and IDE.

45 47

46```toml48```toml

~~47model = "gpt-5.2"~~49model = "gpt-5.4"

48```50```

49 51

50#### Approval prompts52#### Approval prompts

55approval_policy = "on-request"57approval_policy = "on-request"

56```58```

57 59

60For behavior differences between `untrusted`, `on-request`, and `never`, see [Run without approval prompts](https://developers.openai.com/codex/agent-approvals-security#run-without-approval-prompts) and [Common sandbox and approval combinations](https://developers.openai.com/codex/agent-approvals-security#common-sandbox-and-approval-combinations).

58#### Sandbox level62#### Sandbox level

59 63

60Adjust how much filesystem and network access Codex has while executing commands.64Adjust how much filesystem and network access Codex has while executing commands.

63sandbox_mode = "workspace-write"67sandbox_mode = "workspace-write"

64```68```

65 69

70For mode-by-mode behavior (including protected `.git`/`.codex` paths and network defaults), see [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).

72#### Windows sandbox mode

74When running Codex natively on Windows, set the native sandbox mode to `elevated` in the `windows` table. Use `unelevated` only if you don't have administrator permissions or if elevated setup fails.

76```toml

77[windows]

78sandbox = "elevated" # Recommended

79# sandbox = "unelevated" # Fallback if admin permissions/setup are unavailable

80```

66#### Web search mode82#### Web search mode

67 83

68Codex enables web search by default for local tasks and serves results from a web search cache. The cache is an OpenAI-maintained index of web results, so cached mode returns pre-indexed results instead of fetching live pages. This reduces exposure to prompt injection from arbitrary live content, but you should still treat web results as untrusted. If you are using `--yolo` or another [full access sandbox setting](https://developers.openai.com/codex/security), web search defaults to live results. Choose a mode with `web_search`:84Codex enables web search by default for local tasks and serves results from a web search cache. The cache is an OpenAI-maintained index of web results, so cached mode returns pre-indexed results instead of fetching live pages. This reduces exposure to prompt injection from arbitrary live content, but you should still treat web results as untrusted. If you are using `--yolo` or another [full access sandbox setting](https://developers.openai.com/codex/agent-approvals-security#common-sandbox-and-approval-combinations), web search defaults to live results. Choose a mode with `web_search`:

69 85

70- `"cached"` (default) serves results from the web search cache.86- `"cached"` (default) serves results from the web search cache.

71- `"live"` fetches the most recent data from the web (same as `--search`).87- `"live"` fetches the most recent data from the web (same as `--search`).

131 147

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

133| -------------------- | :-------------------: | ------------ | ---------------------------------------------------------------------------------------- |149| -------------------- | :-------------------: | ------------ | ---------------------------------------------------------------------------------------- |

config-reference.md +1175 −338

Details

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/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).

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

10| --- | --- | --- |12| --- | --- | --- |

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. |

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

14| `approval_policy` | `untrusted | on-request | never` | Controls when Codex pauses for approval before executing commands. `on-failure` is deprecated; use `on-request` for interactive runs or `never` for non-interactive runs. |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. |

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. |

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

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

24| `approval_policy.reject.sandbox_approval` | `boolean` | When `true`, sandbox escalation approval prompts are auto-rejected. |

25| `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. |

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

29| `apps.<id>.default_tools_enabled` | `boolean` | Default enabled state for tools in this app unless a per-tool override exists. |

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

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

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

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

~~24| `experimental_use_freeform_apply_patch` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform` or `codex --enable apply_patch_freeform`. |~~

~~26| `features.apply_patch_freeform` | `boolean` | Expose the freeform `apply_patch` tool (experimental). |~~

28| `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). |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). |

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

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). |

55| `features.image_detail_original` | `boolean` | Allow image outputs with `detail = "original"` on supported models (under development). |

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

57| `features.multi_agent` | `boolean` | Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait`, `close_agent`, and `spawn_agents_on_csv`) (experimental; off by default). |

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

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

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

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

71| `features.sqlite` | `boolean` | Enable SQLite-backed state persistence (stable; on by default). |

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

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

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

~~54| `include_apply_patch_tool` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`. |~~

89| `mcp_oauth_callback_url` | `string` | Optional redirect URI override for MCP OAuth login (for example, a devbox ingress URL). `mcp_oauth_callback_port` still controls the callback listener port. |

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

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

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

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

158| `permissions.network.admin_url` | `string` | Admin endpoint for the managed network proxy. |

159| `permissions.network.allow_local_binding` | `boolean` | Permit local bind/listen operations through the managed proxy. |

160| `permissions.network.allow_unix_sockets` | `array<string>` | Allowlist of Unix socket paths permitted through the managed proxy. |

161| `permissions.network.allow_upstream_proxy` | `boolean` | Allow the managed proxy to chain to another upstream proxy. |

162| `permissions.network.allowed_domains` | `array<string>` | Allowlist of domains permitted through the managed proxy. |

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

164| `permissions.network.dangerously_allow_non_loopback_admin` | `boolean` | Permit non-loopback bind addresses for the managed proxy admin listener. |

165| `permissions.network.dangerously_allow_non_loopback_proxy` | `boolean` | Permit non-loopback bind addresses for the managed proxy listener. |

166| `permissions.network.denied_domains` | `array<string>` | Denylist of domains blocked by the managed proxy. |

167| `permissions.network.enable_socks5` | `boolean` | Expose a SOCKS5 listener from the managed network proxy. |

168| `permissions.network.enable_socks5_udp` | `boolean` | Allow UDP over the SOCKS5 listener when enabled. |

169| `permissions.network.enabled` | `boolean` | Enable the managed network proxy configuration for subprocesses. |

171| `permissions.network.proxy_url` | `string` | HTTP proxy endpoint used by the managed network proxy. |

172| `permissions.network.socks_url` | `string` | SOCKS5 proxy endpoint used by the managed network proxy. |

126| `profiles.<name>.include_apply_patch_tool` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`. |179| `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). |

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

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

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

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

153| `tui` | `table` | TUI-specific options such as enabling inline desktop notifications. |214| `tui` | `table` | TUI-specific options such as enabling inline desktop notifications. |

217| `tui.model_availability_nux.<model>` | `integer` | Internal startup-tooltip state keyed by model slug. |

156| `tui.notification_method` | `auto | osc9 | bel` | Notification method for unfocused terminal notifications (default: auto). |218| `tui.notification_method` | `auto | osc9 | bel` | Notification method for unfocused terminal notifications (default: auto). |

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

160| `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| `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. |

162 226

163Key227Key

164 228

186 250

187Key251Key

188 252

189`agents.max_threads`253`agents.<name>.nickname_candidates`

190 254

191Type / Values255Type / Values

192 256

193`number`257`array<string>`

194 258

195Details259Details

196 260

197Maximum number of agent threads that can be open concurrently.261Optional pool of display nicknames for spawned agents in that role.

198 262

199Key263Key

200 264

201`approval_policy`265`agents.job_max_runtime_seconds`

202 266

203Type / Values267Type / Values

204 268

205`untrusted | on-request | never`269`number`

206 270

207Details271Details

208 272

209Controls when Codex pauses for approval before executing commands. `on-failure` is deprecated; use `on-request` for interactive runs or `never` for non-interactive runs.273Default per-worker timeout for `spawn_agents_on_csv` jobs. When unset, the tool falls back to 1800 seconds per worker.

210 274

211Key275Key

212 276

213`apps.<id>.disabled_reason`277`agents.max_depth`

214 278

215Type / Values279Type / Values

216 280

217`unknown | user`281`number`

218 282

219Details283Details

220 284

221Optional reason attached when an app/connector is disabled.285Maximum nesting depth allowed for spawned agent threads (root sessions start at depth 0; default: 1).

222 286

223Key287Key

224 288

225`apps.<id>.enabled`289`agents.max_threads`

226 290

227Type / Values291Type / Values

228 292

229`boolean`293`number`

230 294

231Details295Details

232 296

233Enable or disable a specific app/connector by id (default: true).297Maximum number of agent threads that can be open concurrently.

234 298

235Key299Key

236 300

237`chatgpt_base_url`301`allow_login_shell`

238 302

239Type / Values303Type / Values

240 304

241`string`305`boolean`

242 306

243Details307Details

244 308

245Override the base URL used during the ChatGPT login flow.309Allow 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.

246 310

247Key311Key

248 312

249`check_for_update_on_startup`313`analytics.enabled`

250 314

251Type / Values315Type / Values

252 316

254 318

255Details319Details

256 320

257Check for Codex updates on startup (set to false only when updates are centrally managed).321Enable or disable analytics for this machine/profile. When unset, the client default applies.

258 322

259Key323Key

260 324

261`cli_auth_credentials_store`325`approval_policy`

262 326

263Type / Values327Type / Values

264 328

265`file | keyring | auto`329`untrusted | on-request | never | { reject = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool } }`

266 330

267Details331Details

268 332

269Control where the CLI stores cached credentials (file-based auth.json vs OS keychain).333Controls 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.

270 334

271Key335Key

272 336

273`compact_prompt`337`approval_policy.reject.mcp_elicitations`

274 338

275Type / Values339Type / Values

276 340

277`string`341`boolean`

278 342

279Details343Details

280 344

281Inline override for the history compaction prompt.345When `true`, MCP elicitation prompts are auto-rejected instead of shown to the user.

282 346

283Key347Key

284 348

285`developer_instructions`349`approval_policy.reject.rules`

286 350

287Type / Values351Type / Values

288 352

289`string`353`boolean`

290 354

291Details355Details

292 356

293Additional developer instructions injected into the session (optional).357When `true`, approvals triggered by execpolicy `prompt` rules are auto-rejected.

294 358

295Key359Key

296 360

297`disable_paste_burst`361`approval_policy.reject.sandbox_approval`

298 362

299Type / Values363Type / Values

300 364

302 366

303Details367Details

304 368

305Disable burst-paste detection in the TUI.369When `true`, sandbox escalation approval prompts are auto-rejected.

306 370

307Key371Key

308 372

309`experimental_compact_prompt_file`373`apps._default.destructive_enabled`

310 374

311Type / Values375Type / Values

312 376

313`string (path)`377`boolean`

314 378

315Details379Details

316 380

317Load the compaction prompt override from a file (experimental).381Default allow/deny for app tools with `destructive_hint = true`.

318 382

319Key383Key

320 384

321`experimental_use_freeform_apply_patch`385`apps._default.enabled`

322 386

323Type / Values387Type / Values

324 388

326 390

327Details391Details

328 392

329Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform` or `codex --enable apply_patch_freeform`.393Default app enabled state for all apps unless overridden per app.

330 394

331Key395Key

332 396

333`experimental_use_unified_exec_tool`397`apps._default.open_world_enabled`

334 398

335Type / Values399Type / Values

336 400

338 402

339Details403Details

340 404

341Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`.405Default allow/deny for app tools with `open_world_hint = true`.

342 406

343Key407Key

344 408

345`features.apply_patch_freeform`409`apps.<id>.default_tools_approval_mode`

346 410

347Type / Values411Type / Values

348 412

349`boolean`413`auto | prompt | approve`

350 414

351Details415Details

352 416

353Expose the freeform `apply_patch` tool (experimental).417Default approval behavior for tools in this app unless a per-tool override exists.

354 418

355Key419Key

356 420

357`features.apps`421`apps.<id>.default_tools_enabled`

358 422

359Type / Values423Type / Values

360 424

362 426

363Details427Details

364 428

365Enable ChatGPT Apps/connectors support (experimental).429Default enabled state for tools in this app unless a per-tool override exists.

366 430

367Key431Key

368 432

369`features.apps_mcp_gateway`433`apps.<id>.destructive_enabled`

370 434

371Type / Values435Type / Values

372 436

374 438

375Details439Details

376 440

377Route Apps MCP calls through the OpenAI connectors MCP gateway (`https://api.openai.com/v1/connectors/mcp/`) instead of legacy routing (experimental).441Allow or block tools in this app that advertise `destructive_hint = true`.

378 442

379Key443Key

380 444

381`features.child_agents_md`445`apps.<id>.enabled`

382 446

383Type / Values447Type / Values

384 448

386 450

387Details451Details

388 452

389Append AGENTS.md scope/precedence guidance even when no AGENTS.md is present (experimental).453Enable or disable a specific app/connector by id (default: true).

390 454

391Key455Key

392 456

393`features.collaboration_modes`457`apps.<id>.open_world_enabled`

394 458

395Type / Values459Type / Values

396 460

398 462

399Details463Details

400 464

401Enable collaboration modes such as plan mode (stable; on by default).465Allow or block tools in this app that advertise `open_world_hint = true`.

402 466

403Key467Key

404 468

405`features.elevated_windows_sandbox`469`apps.<id>.tools.<tool>.approval_mode`

406 470

407Type / Values471Type / Values

408 472

409`boolean`473`auto | prompt | approve`

410 474

411Details475Details

412 476

413Enable the elevated Windows sandbox pipeline (experimental).477Per-tool approval behavior override for a single app tool.

414 478

415Key479Key

416 480

417`features.experimental_windows_sandbox`481`apps.<id>.tools.<tool>.enabled`

418 482

419Type / Values483Type / Values

420 484

422 486

423Details487Details

424 488

425Run the Windows restricted-token sandbox (experimental).489Per-tool enabled override for an app tool (for example `repos/list`).

426 490

427Key491Key

428 492

429`features.multi_agent`493`background_terminal_max_timeout`

430 494

431Type / Values495Type / Values

432 496

433`boolean`497`number`

434 498

435Details499Details

436 500

437Enable multi-agent collaboration tools (`spawn\_agent`, `send\_input`, `resume\_agent`, `wait`, and `close\_agent`) (experimental; off by default).501Maximum poll window in milliseconds for empty `write_stdin` polls (background terminal polling). Default: `300000` (5 minutes). Replaces the older `background_terminal_timeout` key.

438 502

439Key503Key

440 504

441`features.personality`505`chatgpt_base_url`

442 506

443Type / Values507Type / Values

444 508

445`boolean`509`string`

446 510

447Details511Details

448 512

449Enable personality selection controls (stable; on by default).513Override the base URL used during the ChatGPT login flow.

450 514

451Key515Key

452 516

453`features.powershell_utf8`517`check_for_update_on_startup`

454 518

455Type / Values519Type / Values

456 520

458 522

459Details523Details

460 524

461Force PowerShell UTF-8 output (defaults to true).525Check for Codex updates on startup (set to false only when updates are centrally managed).

462 526

463Key527Key

464 528

465`features.remote_models`529`cli_auth_credentials_store`

466 530

467Type / Values531Type / Values

468 532

469`boolean`533`file | keyring | auto`

470 534

471Details535Details

472 536

473Refresh remote model list before showing readiness (experimental).537Control where the CLI stores cached credentials (file-based auth.json vs OS keychain).

474 538

475Key539Key

476 540

477`features.request_rule`541`commit_attribution`

478 542

479Type / Values543Type / Values

480 544

481`boolean`545`string`

482 546

483Details547Details

484 548

485Enable Smart approvals (`prefix_rule` suggestions on escalation requests; stable; on by default).549Override the commit co-author trailer text. Set an empty string to disable automatic attribution.

486 550

487Key551Key

488 552

489`features.runtime_metrics`553`compact_prompt`

490 554

491Type / Values555Type / Values

492 556

493`boolean`557`string`

494 558

495Details559Details

496 560

497Show runtime metrics summary in TUI turn separators (experimental).561Inline override for the history compaction prompt.

498 562

499Key563Key

500 564

501`features.search_tool`565`developer_instructions`

502 566

503Type / Values567Type / Values

504 568

505`boolean`569`string`

506 570

507Details571Details

508 572

509Enable `search_tool_bm25` for Apps tool discovery before invoking app MCP tools (experimental).573Additional developer instructions injected into the session (optional).

510 574

511Key575Key

512 576

513`features.shell_snapshot`577`disable_paste_burst`

514 578

515Type / Values579Type / Values

516 580

518 582

519Details583Details

520 584

521Snapshot shell environment to speed up repeated commands (beta).585Disable burst-paste detection in the TUI.

522 586

523Key587Key

524 588

525`features.shell_tool`589`experimental_compact_prompt_file`

526 590

527Type / Values591Type / Values

528 592

529`boolean`593`string (path)`

530 594

531Details595Details

532 596

533Enable the default `shell` tool for running commands (stable; on by default).597Load the compaction prompt override from a file (experimental).

534 598

535Key599Key

536 600

537`features.unified_exec`601`experimental_use_unified_exec_tool`

538 602

539Type / Values603Type / Values

540 604

542 606

543Details607Details

544 608

545Use the unified PTY-backed exec tool (beta).609Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`.

546 610

547Key611Key

548 612

549`features.use_linux_sandbox_bwrap`613`features.apps`

550 614

551Type / Values615Type / Values

552 616

554 618

555Details619Details

556 620

557Use the bubblewrap-based Linux sandbox pipeline (experimental; off by default).621Enable ChatGPT Apps/connectors support (experimental).

558 622

559Key623Key

560 624

561`features.web_search`625`features.apps_mcp_gateway`

562 626

563Type / Values627Type / Values

564 628

566 630

567Details631Details

568 632

569Deprecated legacy toggle; prefer the top-level `web_search` setting.633Route Apps MCP calls through the OpenAI connectors MCP gateway (`https://api.openai.com/v1/connectors/mcp/`) instead of legacy routing (experimental).

570 634

571Key635Key

572 636

573`features.web_search_cached`637`features.artifact`

574 638

575Type / Values639Type / Values

576 640

578 642

579Details643Details

580 644

581Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "cached"`.645Enable native artifact tools such as slides and spreadsheets (under development).

582 646

583Key647Key

584 648

585`features.web_search_request`649`features.child_agents_md`

586 650

587Type / Values651Type / Values

588 652

590 654

591Details655Details

592 656

593Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "live"`.657Append AGENTS.md scope/precedence guidance even when no AGENTS.md is present (experimental).

594 658

595Key659Key

596 660

597`feedback.enabled`661`features.collaboration_modes`

598 662

599Type / Values663Type / Values

600 664

602 666

603Details667Details

604 668

605Enable feedback submission via `/feedback` across Codex surfaces (default: true).669Legacy toggle for collaboration modes. Plan and default modes are available in current builds without setting this key.

606 670

607Key671Key

608 672

609`file_opener`673`features.default_mode_request_user_input`

610 674

611Type / Values675Type / Values

612 676

613`vscode | vscode-insiders | windsurf | cursor | none`677`boolean`

614 678

615Details679Details

616 680

617URI scheme used to open citations from Codex output (default: `vscode`).681Allow `request_user_input` in default collaboration mode (under development; off by default).

618 682

619Key683Key

620 684

621`forced_chatgpt_workspace_id`685`features.elevated_windows_sandbox`

622 686

623Type / Values687Type / Values

624 688

625`string (uuid)`689`boolean`

626 690

627Details691Details

628 692

629Limit ChatGPT logins to a specific workspace identifier.693Legacy toggle for an earlier elevated Windows sandbox rollout. Current builds do not use it.

630 694

631Key695Key

632 696

633`forced_login_method`697`features.enable_request_compression`

634 698

635Type / Values699Type / Values

636 700

637`chatgpt | api`701`boolean`

638 702

639Details703Details

640 704

641Restrict Codex to a specific authentication method.705Compress streaming request bodies with zstd when supported (stable; on by default).

642 706

643Key707Key

644 708

645`hide_agent_reasoning`709`features.experimental_windows_sandbox`

646 710

647Type / Values711Type / Values

648 712

650 714

651Details715Details

652 716

653Suppress reasoning events in both the TUI and `codex exec` output.717Legacy toggle for an earlier Windows sandbox rollout. Current builds do not use it.

654 718

655Key719Key

656 720

657`history.max_bytes`721`features.fast_mode`

658 722

659Type / Values723Type / Values

660 724

661`number`725`boolean`

662 726

663Details727Details

664 728

665If set, caps the history file size in bytes by dropping oldest entries.729Enable Fast mode selection and the `service_tier = "fast"` path (stable; on by default).

666 730

667Key731Key

668 732

669`history.persistence`733`features.image_detail_original`

670 734

671Type / Values735Type / Values

672 736

673`save-all | none`737`boolean`

674 738

675Details739Details

676 740

677Control whether Codex saves session transcripts to history.jsonl.741Allow image outputs with `detail = "original"` on supported models (under development).

678 742

679Key743Key

680 744

681`include_apply_patch_tool`745`features.image_generation`

682 746

683Type / Values747Type / Values

684 748

686 750

687Details751Details

688 752

689Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`.753Enable the built-in image generation tool (under development).

690 754

691Key755Key

692 756

693`instructions`757`features.multi_agent`

694 758

695Type / Values759Type / Values

696 760

697`string`761`boolean`

698 762

699Details763Details

700 764

701Reserved for future use; prefer `model_instructions_file` or `AGENTS.md`.765Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait`, `close_agent`, and `spawn_agents_on_csv`) (experimental; off by default).

702 766

703Key767Key

704 768

705`log_dir`769`features.personality`

706 770

707Type / Values771Type / Values

708 772

709`string (path)`773`boolean`

710 774

711Details775Details

712 776

713Directory where Codex writes log files (for example `codex-tui.log`); defaults to `$CODEX_HOME/log`.777Enable personality selection controls (stable; on by default).

714 778

715Key779Key

716 780

717`mcp_oauth_callback_port`781`features.powershell_utf8`

718 782

719Type / Values783Type / Values

720 784

721`integer`785`boolean`

722 786

723Details787Details

724 788

725Optional 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.789Force PowerShell UTF-8 output. Enabled by default on Windows and off elsewhere.

726 790

727Key791Key

728 792

729`mcp_oauth_credentials_store`793`features.prevent_idle_sleep`

730 794

731Type / Values795Type / Values

732 796

733`auto | file | keyring`797`boolean`

734 798

735Details799Details

736 800

737Preferred store for MCP OAuth credentials.801Prevent the machine from sleeping while a turn is actively running (experimental; off by default).

738 802

739Key803Key

740 804

741`mcp_servers.<id>.args`805`features.remote_models`

742 806

743Type / Values807Type / Values

744 808

745`array<string>`809`boolean`

746 810

747Details811Details

748 812

749Arguments passed to the MCP stdio server command.813Legacy toggle for an older remote-model readiness flow. Current builds do not use it.

750 814

751Key815Key

752 816

753`mcp_servers.<id>.bearer_token_env_var`817`features.request_rule`

754 818

755Type / Values819Type / Values

756 820

757`string`821`boolean`

758 822

759Details823Details

760 824

761Environment variable sourcing the bearer token for an MCP HTTP server.825Legacy toggle for Smart approvals. Current builds include this behavior by default, so most users can leave this unset.

762 826

763Key827Key

764 828

765`mcp_servers.<id>.command`829`features.responses_websockets`

766 830

767Type / Values831Type / Values

768 832

769`string`833`boolean`

770 834

771Details835Details

772 836

773Launcher command for an MCP stdio server.837Prefer the Responses API WebSocket transport for supported providers (under development).

774 838

775Key839Key

776 840

777`mcp_servers.<id>.cwd`841`features.responses_websockets_v2`

778 842

779Type / Values843Type / Values

780 844

781`string`845`boolean`

782 846

783Details847Details

784 848

785Working directory for the MCP stdio server process.849Enable Responses API WebSocket v2 mode (under development).

786 850

787Key851Key

788 852

789`mcp_servers.<id>.disabled_tools`853`features.runtime_metrics`

790 854

791Type / Values855Type / Values

792 856

793`array<string>`857`boolean`

794 858

795Details859Details

796 860

797Deny list applied after `enabled_tools` for the MCP server.861Show runtime metrics summary in TUI turn separators (experimental).

798 862

799Key863Key

800 864

801`mcp_servers.<id>.enabled`865`features.search_tool`

802 866

803Type / Values867Type / Values

804 868

806 870

807Details871Details

808 872

809Disable an MCP server without removing its configuration.873Legacy toggle for an older Apps discovery flow. Current builds do not use it.

810 874

811Key875Key

812 876

813`mcp_servers.<id>.enabled_tools`877`features.shell_snapshot`

814 878

815Type / Values879Type / Values

816 880

817`array<string>`881`boolean`

818 882

819Details883Details

820 884

821Allow list of tool names exposed by the MCP server.885Snapshot shell environment to speed up repeated commands (stable; on by default).

822 886

823Key887Key

824 888

825`mcp_servers.<id>.env`889`features.shell_tool`

826 890

827Type / Values891Type / Values

828 892

829`map<string,string>`893`boolean`

830 894

831Details895Details

832 896

833Environment variables forwarded to the MCP stdio server.897Enable the default `shell` tool for running commands (stable; on by default).

834 898

835Key899Key

836 900

837`mcp_servers.<id>.env_http_headers`901`features.skill_env_var_dependency_prompt`

838 902

839Type / Values903Type / Values

840 904

841`map<string,string>`905`boolean`

842 906

843Details907Details

844 908

845HTTP headers populated from environment variables for an MCP HTTP server.909Prompt for missing skill environment-variable dependencies (under development).

846 910

847Key911Key

848 912

849`mcp_servers.<id>.env_vars`913`features.skill_mcp_dependency_install`

850 914

851Type / Values915Type / Values

852 916

853`array<string>`917`boolean`

854 918

855Details919Details

856 920

857Additional environment variables to whitelist for an MCP stdio server.921Allow prompting and installing missing MCP dependencies for skills (stable; on by default).

858 922

859Key923Key

860 924

861`mcp_servers.<id>.http_headers`925`features.sqlite`

862 926

863Type / Values927Type / Values

864 928

865`map<string,string>`929`boolean`

866 930

867Details931Details

868 932

869Static HTTP headers included with each MCP HTTP request.933Enable SQLite-backed state persistence (stable; on by default).

870 934

871Key935Key

872 936

873`mcp_servers.<id>.required`937`features.steer`

874 938

875Type / Values939Type / Values

876 940

878 942

879Details943Details

880 944

881When true, fail startup/resume if this enabled MCP server cannot initialize.945Legacy toggle from an earlier Enter/Tab steering rollout. Current builds always use the current steering behavior.

882 946

883Key947Key

884 948

885`mcp_servers.<id>.startup_timeout_ms`949`features.undo`

886 950

887Type / Values951Type / Values

888 952

889`number`953`boolean`

890 954

891Details955Details

892 956

893Alias for `startup_timeout_sec` in milliseconds.957Enable undo support (stable; off by default).

894 958

895Key959Key

896 960

897`mcp_servers.<id>.startup_timeout_sec`961`features.unified_exec`

898 962

899Type / Values963Type / Values

900 964

901`number`965`boolean`

902 966

903Details967Details

904 968

905Override the default 10s startup timeout for an MCP server.969Use the unified PTY-backed exec tool (stable; enabled by default except on Windows).

906 970

907Key971Key

908 972

909`mcp_servers.<id>.tool_timeout_sec`973`features.use_linux_sandbox_bwrap`

910 974

911Type / Values975Type / Values

912 976

913`number`977`boolean`

914 978

915Details979Details

916 980

917Override the default 60s per-tool timeout for an MCP server.981Use the bubblewrap-based Linux sandbox pipeline (experimental; off by default).

918 982

919Key983Key

920 984

921`mcp_servers.<id>.url`985`features.web_search`

922 986

923Type / Values987Type / Values

924 988

925`string`989`boolean`

926 990

927Details991Details

928 992

929Endpoint for an MCP streamable HTTP server.993Deprecated legacy toggle; prefer the top-level `web_search` setting.

930 994

931Key995Key

932 996

933`model`997`features.web_search_cached`

934 998

935Type / Values999Type / Values

936 1000

937`string`1001`boolean`

938 1002

939Details1003Details

940 1004

941Model to use (e.g., `gpt-5-codex`).1005Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "cached"`.

942 1006

943Key1007Key

944 1008

945`model_auto_compact_token_limit`1009`features.web_search_request`

946 1010

947Type / Values1011Type / Values

948 1012

949`number`1013`boolean`

950 1014

951Details1015Details

952 1016

953Token threshold that triggers automatic history compaction (unset uses model defaults).1017Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "live"`.

954 1018

955Key1019Key

956 1020

957`model_context_window`1021`feedback.enabled`

958 1022

959Type / Values1023Type / Values

960 1024

961`number`1025`boolean`

962 1026

963Details1027Details

964 1028

965Context window tokens available to the active model.1029Enable feedback submission via `/feedback` across Codex surfaces (default: true).

966 1030

967Key1031Key

968 1032

969`model_instructions_file`1033`file_opener`

970 1034

971Type / Values1035Type / Values

972 1036

973`string (path)`1037`vscode | vscode-insiders | windsurf | cursor | none`

974 1038

975Details1039Details

976 1040

977Replacement for built-in instructions instead of `AGENTS.md`.1041URI scheme used to open citations from Codex output (default: `vscode`).

978 1042

979Key1043Key

980 1044

981`model_provider`1045`forced_chatgpt_workspace_id`

1046

1047Type / Values

1048

1049`string (uuid)`

1050

1051Details

1052

1053Limit ChatGPT logins to a specific workspace identifier.

1054

1055Key

1056

1057`forced_login_method`

1058

1059Type / Values

1060

1061`chatgpt | api`

1062

1063Details

1064

1065Restrict Codex to a specific authentication method.

1066

1067Key

1068

1069`hide_agent_reasoning`

1070

1071Type / Values

1072

1073`boolean`

1074

1075Details

1076

1077Suppress reasoning events in both the TUI and `codex exec` output.

1078

1079Key

1080

1081`history.max_bytes`

1082

1083Type / Values

1084

1085`number`

1086

1087Details

1088

1089If set, caps the history file size in bytes by dropping oldest entries.

1090

1091Key

1092

1093`history.persistence`

1094

1095Type / Values

1096

1097`save-all | none`

1098

1099Details

1100

1101Control whether Codex saves session transcripts to history.jsonl.

1102

1103Key

1104

1105`instructions`

982 1106

983Type / Values1107Type / Values

984 1108

986 1110

987Details1111Details

988 1112

989Provider id from `model_providers` (default: `openai`).1113Reserved for future use; prefer `model_instructions_file` or `AGENTS.md`.

990 1114

991Key1115Key

992 1116

993`model_providers.<id>.base_url`1117`log_dir`

1118

1119Type / Values

1120

1121`string (path)`

1122

1123Details

1124

1125Directory where Codex writes log files (for example `codex-tui.log`); defaults to `$CODEX_HOME/log`.

1126

1127Key

1128

1129`mcp_oauth_callback_port`

1130

1131Type / Values

1132

1133`integer`

1134

1135Details

1136

1137Optional 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.

1138

1139Key

1140

1141`mcp_oauth_callback_url`

994 1142

995Type / Values1143Type / Values

996 1144

998 1146

999Details1147Details

1000 1148

1001API base URL for the model provider.1149Optional redirect URI override for MCP OAuth login (for example, a devbox ingress URL). `mcp_oauth_callback_port` still controls the callback listener port.

1002 1150

1003Key1151Key

1004 1152

1005`model_providers.<id>.env_http_headers`1153`mcp_oauth_credentials_store`

1006 1154

1007Type / Values1155Type / Values

1008 1156

1009`map<string,string>`1157`auto | file | keyring`

1010 1158

1011Details1159Details

1012 1160

1013HTTP headers populated from environment variables when present.1161Preferred store for MCP OAuth credentials.

1014 1162

1015Key1163Key

1016 1164

1017`model_providers.<id>.env_key`1165`mcp_servers.<id>.args`

1166

1167Type / Values

1168

1169`array<string>`

1170

1171Details

1172

1173Arguments passed to the MCP stdio server command.

1174

1175Key

1176

1177`mcp_servers.<id>.bearer_token_env_var`

1018 1178

1019Type / Values1179Type / Values

1020 1180

1022 1182

1023Details1183Details

1024 1184

1025Environment variable supplying the provider API key.1185Environment variable sourcing the bearer token for an MCP HTTP server.

1026 1186

1027Key1187Key

1028 1188

1029`model_providers.<id>.env_key_instructions`1189`mcp_servers.<id>.command`

1030 1190

1031Type / Values1191Type / Values

1032 1192

1034 1194

1035Details1195Details

1036 1196

1037Optional setup guidance for the provider API key.1197Launcher command for an MCP stdio server.

1038 1198

1039Key1199Key

1040 1200

1041`model_providers.<id>.experimental_bearer_token`1201`mcp_servers.<id>.cwd`

1042 1202

1043Type / Values1203Type / Values

1044 1204

1046 1206

1047Details1207Details

1048 1208

1049Direct bearer token for the provider (discouraged; use `env_key`).1209Working directory for the MCP stdio server process.

1050 1210

1051Key1211Key

1052 1212

1053`model_providers.<id>.http_headers`1213`mcp_servers.<id>.disabled_tools`

1214

1215Type / Values

1216

1217`array<string>`

1218

1219Details

1220

1221Deny list applied after `enabled_tools` for the MCP server.

1222

1223Key

1224

1225`mcp_servers.<id>.enabled`

1226

1227Type / Values

1228

1229`boolean`

1230

1231Details

1232

1233Disable an MCP server without removing its configuration.

1234

1235Key

1236

1237`mcp_servers.<id>.enabled_tools`

1238

1239Type / Values

1240

1241`array<string>`

1242

1243Details

1244

1245Allow list of tool names exposed by the MCP server.

1246

1247Key

1248

1249`mcp_servers.<id>.env`

1054 1250

1055Type / Values1251Type / Values

1056 1252

1058 1254

1059Details1255Details

1060 1256

1061Static HTTP headers added to provider requests.1257Environment variables forwarded to the MCP stdio server.

1062 1258

1063Key1259Key

1064 1260

1065`model_providers.<id>.name`1261`mcp_servers.<id>.env_http_headers`

1066 1262

1067Type / Values1263Type / Values

1068 1264

1069`string`1265`map<string,string>`

1070 1266

1071Details1267Details

1072 1268

1073Display name for a custom model provider.1269HTTP headers populated from environment variables for an MCP HTTP server.

1074 1270

1075Key1271Key

1076 1272

1077`model_providers.<id>.query_params`1273`mcp_servers.<id>.env_vars`

1274

1275Type / Values

1276

1277`array<string>`

1278

1279Details

1280

1281Additional environment variables to whitelist for an MCP stdio server.

1282

1283Key

1284

1285`mcp_servers.<id>.http_headers`

1078 1286

1079Type / Values1287Type / Values

1080 1288

1082 1290

1083Details1291Details

1084 1292

1085Extra query parameters appended to provider requests.1293Static HTTP headers included with each MCP HTTP request.

1086 1294

1087Key1295Key

1088 1296

1089`model_providers.<id>.request_max_retries`1297`mcp_servers.<id>.oauth_resource`

1090 1298

1091Type / Values1299Type / Values

1092 1300

1093`number`1301`string`

1094 1302

1095Details1303Details

1096 1304

1097Retry count for HTTP requests to the provider (default: 4).1305Optional RFC 8707 OAuth resource parameter to include during MCP login.

1098 1306

1099Key1307Key

1100 1308

1101`model_providers.<id>.requires_openai_auth`1309`mcp_servers.<id>.required`

1102 1310

1103Type / Values1311Type / Values

1104 1312

1106 1314

1107Details1315Details

1108 1316

1109The provider uses OpenAI authentication (defaults to false).1317When true, fail startup/resume if this enabled MCP server cannot initialize.

1110 1318

1111Key1319Key

1112 1320

1113`model_providers.<id>.stream_idle_timeout_ms`1321`mcp_servers.<id>.scopes`

1322

1323Type / Values

1324

1325`array<string>`

1326

1327Details

1328

1329OAuth scopes to request when authenticating to that MCP server.

1330

1331Key

1332

1333`mcp_servers.<id>.startup_timeout_ms`

1334

1335Type / Values

1336

1337`number`

1338

1339Details

1340

1341Alias for `startup_timeout_sec` in milliseconds.

1342

1343Key

1344

1345`mcp_servers.<id>.startup_timeout_sec`

1346

1347Type / Values

1348

1349`number`

1350

1351Details

1352

1353Override the default 10s startup timeout for an MCP server.

1354

1355Key

1356

1357`mcp_servers.<id>.tool_timeout_sec`

1358

1359Type / Values

1360

1361`number`

1362

1363Details

1364

1365Override the default 60s per-tool timeout for an MCP server.

1366

1367Key

1368

1369`mcp_servers.<id>.url`

1370

1371Type / Values

1372

1373`string`

1374

1375Details

1376

1377Endpoint for an MCP streamable HTTP server.

1378

1379Key

1380

1381`model`

1382

1383Type / Values

1384

1385`string`

1386

1387Details

1388

1389Model to use (e.g., `gpt-5-codex`).

1390

1391Key

1392

1393`model_auto_compact_token_limit`

1394

1395Type / Values

1396

1397`number`

1398

1399Details

1400

1401Token threshold that triggers automatic history compaction (unset uses model defaults).

1402

1403Key

1404

1405`model_catalog_json`

1406

1407Type / Values

1408

1409`string (path)`

1410

1411Details

1412

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

1414

1415Key

1416

1417`model_context_window`

1418

1419Type / Values

1420

1421`number`

1422

1423Details

1424

1425Context window tokens available to the active model.

1426

1427Key

1428

1429`model_instructions_file`

1430

1431Type / Values

1432

1433`string (path)`

1434

1435Details

1436

1437Replacement for built-in instructions instead of `AGENTS.md`.

1438

1439Key

1440

1441`model_provider`

1442

1443Type / Values

1444

1445`string`

1446

1447Details

1448

1449Provider id from `model_providers` (default: `openai`).

1450

1451Key

1452

1453`model_providers.<id>.base_url`

1454

1455Type / Values

1456

1457`string`

1458

1459Details

1460

1461API base URL for the model provider.

1462

1463Key

1464

1465`model_providers.<id>.env_http_headers`

1466

1467Type / Values

1468

1469`map<string,string>`

1470

1471Details

1472

1473HTTP headers populated from environment variables when present.

1474

1475Key

1476

1477`model_providers.<id>.env_key`

1478

1479Type / Values

1480

1481`string`

1482

1483Details

1484

1485Environment variable supplying the provider API key.

1486

1487Key

1488

1489`model_providers.<id>.env_key_instructions`

1490

1491Type / Values

1492

1493`string`

1494

1495Details

1496

1497Optional setup guidance for the provider API key.

1498

1499Key

1500

1501`model_providers.<id>.experimental_bearer_token`

1502

1503Type / Values

1504

1505`string`

1506

1507Details

1508

1509Direct bearer token for the provider (discouraged; use `env_key`).

1510

1511Key

1512

1513`model_providers.<id>.http_headers`

1514

1515Type / Values

1516

1517`map<string,string>`

1518

1519Details

1520

1521Static HTTP headers added to provider requests.

1522

1523Key

1524

1525`model_providers.<id>.name`

1526

1527Type / Values

1528

1529`string`

1530

1531Details

1532

1533Display name for a custom model provider.

1534

1535Key

1536

1537`model_providers.<id>.query_params`

1538

1539Type / Values

1540

1541`map<string,string>`

1542

1543Details

1544

1545Extra query parameters appended to provider requests.

1546

1547Key

1548

1549`model_providers.<id>.request_max_retries`

1550

1551Type / Values

1552

1553`number`

1554

1555Details

1556

1557Retry count for HTTP requests to the provider (default: 4).

1558

1559Key

1560

1561`model_providers.<id>.requires_openai_auth`

1562

1563Type / Values

1564

1565`boolean`

1566

1567Details

1568

1569The provider uses OpenAI authentication (defaults to false).

1570

1571Key

1572

1573`model_providers.<id>.stream_idle_timeout_ms`

1574

1575Type / Values

1576

1577`number`

1578

1579Details

1580

1581Idle timeout for SSE streams in milliseconds (default: 300000).

1582

1583Key

1584

1585`model_providers.<id>.stream_max_retries`

1586

1587Type / Values

1588

1589`number`

1590

1591Details

1592

1593Retry count for SSE streaming interruptions (default: 5).

1594

1595Key

1596

1597`model_providers.<id>.supports_websockets`

1598

1599Type / Values

1600

1601`boolean`

1602

1603Details

1604

1605Whether that provider supports the Responses API WebSocket transport.

1606

1607Key

1608

1609`model_providers.<id>.wire_api`

1610

1611Type / Values

1612

1613`responses`

1614

1615Details

1616

1617Protocol used by the provider. `responses` is the only supported value, and it is the default when omitted.

1618

1619Key

1620

1621`model_reasoning_effort`

1622

1623Type / Values

1624

1625`minimal | low | medium | high | xhigh`

1626

1627Details

1628

1629Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent).

1630

1631Key

1632

1633`model_reasoning_summary`

1634

1635Type / Values

1636

1637`auto | concise | detailed | none`

1638

1639Details

1640

1641Select reasoning summary detail or disable summaries entirely.

1642

1643Key

1644

1645`model_supports_reasoning_summaries`

1646

1647Type / Values

1648

1649`boolean`

1650

1651Details

1652

1653Force Codex to send or not send reasoning metadata.

1654

1655Key

1656

1657`model_verbosity`

1658

1659Type / Values

1660

1661`low | medium | high`

1662

1663Details

1664

1665Optional GPT-5 Responses API verbosity override; when unset, the selected model/preset default is used.

1666

1667Key

1668

1669`notice.hide_full_access_warning`

1670

1671Type / Values

1672

1673`boolean`

1674

1675Details

1676

1677Track acknowledgement of the full access warning prompt.

1678

1679Key

1680

1681`notice.hide_gpt-5.1-codex-max_migration_prompt`

1682

1683Type / Values

1684

1685`boolean`

1686

1687Details

1688

1689Track acknowledgement of the gpt-5.1-codex-max migration prompt.

1690

1691Key

1692

1693`notice.hide_gpt5_1_migration_prompt`

1694

1695Type / Values

1696

1697`boolean`

1698

1699Details

1700

1701Track acknowledgement of the GPT-5.1 migration prompt.

1702

1703Key

1704

1705`notice.hide_rate_limit_model_nudge`

1706

1707Type / Values

1708

1709`boolean`

1710

1711Details

1712

1713Track opt-out of the rate limit model switch reminder.

1714

1715Key

1716

1717`notice.hide_world_writable_warning`

1718

1719Type / Values

1720

1721`boolean`

1722

1723Details

1724

1725Track acknowledgement of the Windows world-writable directories warning.

1726

1727Key

1728

1729`notice.model_migrations`

1730

1731Type / Values

1732

1733`map<string,string>`

1734

1735Details

1736

1737Track acknowledged model migrations as old->new mappings.

1738

1739Key

1740

1741`notify`

1742

1743Type / Values

1744

1745`array<string>`

1746

1747Details

1748

1749Command invoked for notifications; receives a JSON payload from Codex.

1750

1751Key

1752

1753`oss_provider`

1754

1755Type / Values

1756

1757`lmstudio | ollama`

1758

1759Details

1760

1761Default local provider used when running with `--oss` (defaults to prompting if unset).

1762

1763Key

1764

1765`otel.environment`

1766

1767Type / Values

1768

1769`string`

1770

1771Details

1772

1773Environment tag applied to emitted OpenTelemetry events (default: `dev`).

1774

1775Key

1776

1777`otel.exporter`

1778

1779Type / Values

1780

1781`none | otlp-http | otlp-grpc`

1782

1783Details

1784

1785Select the OpenTelemetry exporter and provide any endpoint metadata.

1786

1787Key

1788

1789`otel.exporter.<id>.endpoint`

1790

1791Type / Values

1792

1793`string`

1794

1795Details

1796

1797Exporter endpoint for OTEL logs.

1798

1799Key

1800

1801`otel.exporter.<id>.headers`

1802

1803Type / Values

1804

1805`map<string,string>`

1806

1807Details

1808

1809Static headers included with OTEL exporter requests.

1810

1811Key

1812

1813`otel.exporter.<id>.protocol`

1814

1815Type / Values

1816

1817`binary | json`

1818

1819Details

1820

1821Protocol used by the OTLP/HTTP exporter.

1822

1823Key

1824

1825`otel.exporter.<id>.tls.ca-certificate`

1826

1827Type / Values

1828

1829`string`

1830

1831Details

1832

1833CA certificate path for OTEL exporter TLS.

1834

1835Key

1836

1837`otel.exporter.<id>.tls.client-certificate`

1114 1838

1115Type / Values1839Type / Values

1116 1840

1117`number`1841`string`

1118 1842

1119Details1843Details

1120 1844

1121Idle timeout for SSE streams in milliseconds (default: 300000).1845Client certificate path for OTEL exporter TLS.

1122 1846

1123Key1847Key

1124 1848

1125`model_providers.<id>.stream_max_retries`1849`otel.exporter.<id>.tls.client-private-key`

1126 1850

1127Type / Values1851Type / Values

1128 1852

1129`number`1853`string`

1130 1854

1131Details1855Details

1132 1856

1133Retry count for SSE streaming interruptions (default: 5).1857Client private key path for OTEL exporter TLS.

1134 1858

1135Key1859Key

1136 1860

1137`model_providers.<id>.wire_api`1861`otel.log_user_prompt`

1138 1862

1139Type / Values1863Type / Values

1140 1864

1141`chat | responses`1865`boolean`

1142 1866

1143Details1867Details

1144 1868

1145Protocol used by the provider (defaults to `chat` if omitted).1869Opt in to exporting raw user prompts with OpenTelemetry logs.

1146 1870

1147Key1871Key

1148 1872

1149`model_reasoning_effort`1873`otel.metrics_exporter`

1150 1874

1151Type / Values1875Type / Values

1152 1876

1154 1878

1155Details1879Details

1156 1880

1157Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent).1881Select the OpenTelemetry metrics exporter (defaults to `statsig`).

1158 1882

1159Key1883Key

1160 1884

1161`model_reasoning_summary`1885`otel.trace_exporter`

1162 1886

1163Type / Values1887Type / Values

1164 1888

1166 1890

1167Details1891Details

1168 1892

1169Select reasoning summary detail or disable summaries entirely.1893Select the OpenTelemetry trace exporter and provide any endpoint metadata.

1170 1894

1171Key1895Key

1172 1896

1173`model_supports_reasoning_summaries`1897`otel.trace_exporter.<id>.endpoint`

1174 1898

1175Type / Values1899Type / Values

1176 1900

1177`boolean`1901`string`

1178 1902

1179Details1903Details

1180 1904

1181Force Codex to send or not send reasoning metadata.1905Trace exporter endpoint for OTEL logs.

1182 1906

1183Key1907Key

1184 1908

1185`model_verbosity`1909`otel.trace_exporter.<id>.headers`

1186 1910

1187Type / Values1911Type / Values

1188 1912

1189`low | medium | high`1913`map<string,string>`

1190 1914

1191Details1915Details

1192 1916

1193Control GPT-5 Responses API verbosity (defaults to `medium`).1917Static headers included with OTEL trace exporter requests.

1194 1918

1195Key1919Key

1196 1920

1197`notice.hide_full_access_warning`1921`otel.trace_exporter.<id>.protocol`

1198 1922

1199Type / Values1923Type / Values

1200 1924

1201`boolean`1925`binary | json`

1202 1926

1203Details1927Details

1204 1928

1205Track acknowledgement of the full access warning prompt.1929Protocol used by the OTLP/HTTP trace exporter.

1206 1930

1207Key1931Key

1208 1932

1209`notice.hide_gpt-5.1-codex-max_migration_prompt`1933`otel.trace_exporter.<id>.tls.ca-certificate`

1210 1934

1211Type / Values1935Type / Values

1212 1936

1213`boolean`1937`string`

1214 1938

1215Details1939Details

1216 1940

1217Track acknowledgement of the gpt-5.1-codex-max migration prompt.1941CA certificate path for OTEL trace exporter TLS.

1218 1942

1219Key1943Key

1220 1944

1221`notice.hide_gpt5_1_migration_prompt`1945`otel.trace_exporter.<id>.tls.client-certificate`

1222 1946

1223Type / Values1947Type / Values

1224 1948

1225`boolean`1949`string`

1226 1950

1227Details1951Details

1228 1952

1229Track acknowledgement of the GPT-5.1 migration prompt.1953Client certificate path for OTEL trace exporter TLS.

1230 1954

1231Key1955Key

1232 1956

1233`notice.hide_rate_limit_model_nudge`1957`otel.trace_exporter.<id>.tls.client-private-key`

1234 1958

1235Type / Values1959Type / Values

1236 1960

1237`boolean`1961`string`

1238 1962

1239Details1963Details

1240 1964

1241Track opt-out of the rate limit model switch reminder.1965Client private key path for OTEL trace exporter TLS.

1242 1966

1243Key1967Key

1244 1968

1245`notice.hide_world_writable_warning`1969`permissions.network.admin_url`

1246 1970

1247Type / Values1971Type / Values

1248 1972

1249`boolean`1973`string`

1250 1974

1251Details1975Details

1252 1976

1253Track acknowledgement of the Windows world-writable directories warning.1977Admin endpoint for the managed network proxy.

1254 1978

1255Key1979Key

1256 1980

1257`notice.model_migrations`1981`permissions.network.allow_local_binding`

1258 1982

1259Type / Values1983Type / Values

1260 1984

1261`map<string,string>`1985`boolean`

1262 1986

1263Details1987Details

1264 1988

1265Track acknowledged model migrations as old->new mappings.1989Permit local bind/listen operations through the managed proxy.

1266 1990

1267Key1991Key

1268 1992

1269`notify`1993`permissions.network.allow_unix_sockets`

1270 1994

1271Type / Values1995Type / Values

1272 1996

1274 1998

1275Details1999Details

1276 2000

1277Command invoked for notifications; receives a JSON payload from Codex.2001Allowlist of Unix socket paths permitted through the managed proxy.

1278 2002

1279Key2003Key

1280 2004

1281`oss_provider`2005`permissions.network.allow_upstream_proxy`

1282 2006

1283Type / Values2007Type / Values

1284 2008

1285`lmstudio | ollama`2009`boolean`

1286 2010

1287Details2011Details

1288 2012

1289Default local provider used when running with `--oss` (defaults to prompting if unset).2013Allow the managed proxy to chain to another upstream proxy.

1290 2014

1291Key2015Key

1292 2016

1293`otel.environment`2017`permissions.network.allowed_domains`

1294 2018

1295Type / Values2019Type / Values

1296 2020

1297`string`2021`array<string>`

1298 2022

1299Details2023Details

1300 2024

1301Environment tag applied to emitted OpenTelemetry events (default: `dev`).2025Allowlist of domains permitted through the managed proxy.

1302 2026

1303Key2027Key

1304 2028

1305`otel.exporter`2029`permissions.network.dangerously_allow_all_unix_sockets`

1306 2030

1307Type / Values2031Type / Values

1308 2032

1309`none | otlp-http | otlp-grpc`2033`boolean`

1310 2034

1311Details2035Details

1312 2036

1313Select the OpenTelemetry exporter and provide any endpoint metadata.2037Allow the proxy to use arbitrary Unix sockets instead of the default restricted set.

1314 2038

1315Key2039Key

1316 2040

1317`otel.exporter.<id>.endpoint`2041`permissions.network.dangerously_allow_non_loopback_admin`

1318 2042

1319Type / Values2043Type / Values

1320 2044

1321`string`2045`boolean`

1322 2046

1323Details2047Details

1324 2048

1325Exporter endpoint for OTEL logs.2049Permit non-loopback bind addresses for the managed proxy admin listener.

1326 2050

1327Key2051Key

1328 2052

1329`otel.exporter.<id>.headers`2053`permissions.network.dangerously_allow_non_loopback_proxy`

1330 2054

1331Type / Values2055Type / Values

1332 2056

1333`map<string,string>`2057`boolean`

1334 2058

1335Details2059Details

1336 2060

1337Static headers included with OTEL exporter requests.2061Permit non-loopback bind addresses for the managed proxy listener.

1338 2062

1339Key2063Key

1340 2064

1341`otel.exporter.<id>.protocol`2065`permissions.network.denied_domains`

1342 2066

1343Type / Values2067Type / Values

1344 2068

1345`binary | json`2069`array<string>`

1346 2070

1347Details2071Details

1348 2072

1349Protocol used by the OTLP/HTTP exporter.2073Denylist of domains blocked by the managed proxy.

1350 2074

1351Key2075Key

1352 2076

1353`otel.exporter.<id>.tls.ca-certificate`2077`permissions.network.enable_socks5`

1354 2078

1355Type / Values2079Type / Values

1356 2080

1357`string`2081`boolean`

1358 2082

1359Details2083Details

1360 2084

1361CA certificate path for OTEL exporter TLS.2085Expose a SOCKS5 listener from the managed network proxy.

1362 2086

1363Key2087Key

1364 2088

1365`otel.exporter.<id>.tls.client-certificate`2089`permissions.network.enable_socks5_udp`

1366 2090

1367Type / Values2091Type / Values

1368 2092

1369`string`2093`boolean`

1370 2094

1371Details2095Details

1372 2096

1373Client certificate path for OTEL exporter TLS.2097Allow UDP over the SOCKS5 listener when enabled.

1374 2098

1375Key2099Key

1376 2100

1377`otel.exporter.<id>.tls.client-private-key`2101`permissions.network.enabled`

1378 2102

1379Type / Values2103Type / Values

1380 2104

1381`string`2105`boolean`

1382 2106

1383Details2107Details

1384 2108

1385Client private key path for OTEL exporter TLS.2109Enable the managed network proxy configuration for subprocesses.

1386 2110

1387Key2111Key

1388 2112

1389`otel.log_user_prompt`2113`permissions.network.mode`

1390 2114

1391Type / Values2115Type / Values

1392 2116

1393`boolean`2117`limited | full`

1394 2118

1395Details2119Details

1396 2120

1397Opt in to exporting raw user prompts with OpenTelemetry logs.2121Network proxy mode used for subprocess traffic.

1398 2122

1399Key2123Key

1400 2124

1401`otel.trace_exporter`2125`permissions.network.proxy_url`

1402 2126

1403Type / Values2127Type / Values

1404 2128

1405`none | otlp-http | otlp-grpc`2129`string`

1406 2130

1407Details2131Details

1408 2132

1409Select the OpenTelemetry trace exporter and provide any endpoint metadata.2133HTTP proxy endpoint used by the managed network proxy.

1410 2134

1411Key2135Key

1412 2136

1413`otel.trace_exporter.<id>.endpoint`2137`permissions.network.socks_url`

1414 2138

1415Type / Values2139Type / Values

1416 2140

1418 2142

1419Details2143Details

1420 2144

1421Trace exporter endpoint for OTEL logs.2145SOCKS5 proxy endpoint used by the managed network proxy.

1422 2146

1423Key2147Key

1424 2148

1425`otel.trace_exporter.<id>.headers`2149`personality`

1426 2150

1427Type / Values2151Type / Values

1428 2152

1429`map<string,string>`2153`none | friendly | pragmatic`

1430 2154

1431Details2155Details

1432 2156

1433Static headers included with OTEL trace exporter requests.2157Default communication style for models that advertise `supportsPersonality`; can be overridden per thread/turn or via `/personality`.

1434 2158

1435Key2159Key

1436 2160

1437`otel.trace_exporter.<id>.protocol`2161`plan_mode_reasoning_effort`

1438 2162

1439Type / Values2163Type / Values

1440 2164

1442 2166

1443Details2167Details

1444 2168

1445Protocol used by the OTLP/HTTP trace exporter.2169Plan-mode-specific reasoning override. When unset, Plan mode uses its built-in preset default.

1446 2170

1447Key2171Key

1448 2172

1449`otel.trace_exporter.<id>.tls.ca-certificate`2173`profile`

1450 2174

1451Type / Values2175Type / Values

1452 2176

1454 2178

1455Details2179Details

1456 2180

1457CA certificate path for OTEL trace exporter TLS.2181Default profile applied at startup (equivalent to `--profile`).

1458 2182

1459Key2183Key

1460 2184

1461`otel.trace_exporter.<id>.tls.client-certificate`2185`profiles.<name>.*`

1462 2186

1463Type / Values2187Type / Values

1464 2188

1465`string`2189`various`

1466 2190

1467Details2191Details

1468 2192

1469Client certificate path for OTEL trace exporter TLS.2193Profile-scoped overrides for any of the supported configuration keys.

1470 2194

1471Key2195Key

1472 2196

1473`otel.trace_exporter.<id>.tls.client-private-key`2197`profiles.<name>.analytics.enabled`

1474 2198

1475Type / Values2199Type / Values

1476 2200

1477`string`2201`boolean`

1478 2202

1479Details2203Details

1480 2204

1481Client private key path for OTEL trace exporter TLS.2205Profile-scoped analytics enablement override.

1482 2206

1483Key2207Key

1484 2208

1485`personality`2209`profiles.<name>.experimental_use_unified_exec_tool`

1486 2210

1487Type / Values2211Type / Values

1488 2212

1489`none | friendly | pragmatic`2213`boolean`

1490 2214

1491Details2215Details

1492 2216

1493Default communication style for models that advertise `supportsPersonality`; can be overridden per thread/turn or via `/personality`.2217Legacy name for enabling unified exec; prefer `[features].unified_exec`.

1494 2218

1495Key2219Key

1496 2220

1497`profile`2221`profiles.<name>.model_catalog_json`

1498 2222

1499Type / Values2223Type / Values

1500 2224

1501`string`2225`string (path)`

1502 2226

1503Details2227Details

1504 2228

1505Default profile applied at startup (equivalent to `--profile`).2229Profile-scoped model catalog JSON path override (applied on startup only; overrides the top-level `model_catalog_json` for that profile).

1506 2230

1507Key2231Key

1508 2232

1509`profiles.<name>.*`2233`profiles.<name>.model_instructions_file`

1510 2234

1511Type / Values2235Type / Values

1512 2236

1513`various`2237`string (path)`

1514 2238

1515Details2239Details

1516 2240

1517Profile-scoped overrides for any of the supported configuration keys.2241Profile-scoped replacement for the built-in instruction file.

1518 2242

1519Key2243Key

1520 2244

1521`profiles.<name>.experimental_use_freeform_apply_patch`2245`profiles.<name>.oss_provider`

1522 2246

1523Type / Values2247Type / Values

1524 2248

1525`boolean`2249`lmstudio | ollama`

1526 2250

1527Details2251Details

1528 2252

1529Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`.2253Profile-scoped OSS provider for `--oss` sessions.

1530 2254

1531Key2255Key

1532 2256

1533`profiles.<name>.experimental_use_unified_exec_tool`2257`profiles.<name>.personality`

1534 2258

1535Type / Values2259Type / Values

1536 2260

1537`boolean`2261`none | friendly | pragmatic`

1538 2262

1539Details2263Details

1540 2264

1541Legacy name for enabling unified exec; prefer `[features].unified_exec`.2265Profile-scoped communication style override for supported models.

1542 2266

1543Key2267Key

1544 2268

1545`profiles.<name>.include_apply_patch_tool`2269`profiles.<name>.plan_mode_reasoning_effort`

1546 2270

1547Type / Values2271Type / Values

1548 2272

1550 2274

1551Details2275Details

1552 2276

1553Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`.2277Profile-scoped Plan-mode reasoning override.

1554 2278

1555Key2279Key

1556 2280

1557`profiles.<name>.oss_provider`2281`profiles.<name>.service_tier`

1558 2282

1559Type / Values2283Type / Values

1560 2284

1561`lmstudio | ollama`2285`flex | fast`

1562 2286

1563Details2287Details

1564 2288

1565Profile-scoped OSS provider for `--oss` sessions.2289Profile-scoped service tier preference for new turns.

1566 2290

1567Key2291Key

1568 2292

1569`profiles.<name>.personality`2293`profiles.<name>.tools_view_image`

1570 2294

1571Type / Values2295Type / Values

1572 2296

1573`none | friendly | pragmatic`2297`boolean`

1574 2298

1575Details2299Details

1576 2300

1577Profile-scoped communication style override for supported models.2301Enable or disable the `view_image` tool in that profile.

1578 2302

1579Key2303Key

1580 2304

1590 2314

1591Key2315Key

1592 2316

2317`profiles.<name>.windows.sandbox`

2318

2319Type / Values

2320

2321`unelevated | elevated`

2322

2323Details

2324

2325Profile-scoped Windows sandbox mode override.

2326

2327Key

2328

1593`project_doc_fallback_filenames`2329`project_doc_fallback_filenames`

1594 2330

1595Type / Values2331Type / Values

1710 2446

1711Key2447Key

1712 2448

2449`service_tier`

2450

2451Type / Values

2452

2453`flex | fast`

2454

2455Details

2456

2457Preferred service tier for new turns. `fast` is honored only when the `features.fast_mode` gate is enabled.

2458

2459Key

2460

1713`shell_environment_policy.exclude`2461`shell_environment_policy.exclude`

1714 2462

1715Type / Values2463Type / Values

1830 2578

1831Key2579Key

1832 2580

2581`sqlite_home`

2582

2583Type / Values

2584

2585`string (path)`

2586

2587Details

2588

2589Directory where Codex stores the SQLite-backed state DB used by agent jobs and other resumable runtime state.

2590

2591Key

2592

1833`suppress_unstable_features_warning`2593`suppress_unstable_features_warning`

1834 2594

1835Type / Values2595Type / Values

1854 2614

1855Key2615Key

1856 2616

2617`tools.view_image`

2618

2619Type / Values

2620

2621`boolean`

2622

2623Details

2624

2625Enable the local-image attachment tool `view_image`.

2626

2627Key

2628

1857`tools.web_search`2629`tools.web_search`

1858 2630

1859Type / Values2631Type / Values

1902 2674

1903Key2675Key

1904 2676

2677`tui.model_availability_nux.<model>`

2678

2679Type / Values

2680

2681`integer`

2682

2683Details

2684

2685Internal startup-tooltip state keyed by model slug.

2686

2687Key

2688

1905`tui.notification_method`2689`tui.notification_method`

1906 2690

1907Type / Values2691Type / Values

1950 2734

1951Key2735Key

1952 2736

2737`tui.theme`

2738

2739Type / Values

2740

2741`string`

2742

2743Details

2744

2745Syntax-highlighting theme override (kebab-case theme name).

2746

2747Key

2748

1953`web_search`2749`web_search`

1954 2750

1955Type / Values2751Type / Values

1972 2768

1973Track Windows onboarding acknowledgement (Windows only).2769Track Windows onboarding acknowledgement (Windows only).

1974 2770

2771Key

2772

2773`windows.sandbox`

2774

2775Type / Values

2776

2777`unelevated | elevated`

2778

2779Details

2780

2781Windows-only native sandbox mode when running Codex natively on Windows.

2782

1975Expand to view all2783Expand to view all

1976 2784

1977You can find the latest JSON schema for `config.toml` [here](https://developers.openai.com/codex/config-schema.json).2785You can find the latest JSON schema for `config.toml` [here](https://developers.openai.com/codex/config-schema.json).

1986 2794

1987## `requirements.toml`2795## `requirements.toml`

1988 2796

1989`requirements.toml` is an admin-enforced configuration file that constrains security-sensitive settings users can’t override. For details, locations, and examples, see [Admin-enforced requirements](https://developers.openai.com/codex/security#admin-enforced-requirements-requirementstoml).2797`requirements.toml` is an admin-enforced configuration file that constrains security-sensitive settings users can't override. For details, locations, and examples, see [Admin-enforced requirements](https://developers.openai.com/codex/enterprise/managed-configuration#admin-enforced-requirements-requirementstoml).

1990 2798

1991For ChatGPT Business and Enterprise users, Codex can also apply cloud-fetched2799For ChatGPT Business and Enterprise users, Codex can also apply cloud-fetched

1992requirements. See the security page for precedence details.2800requirements. See the security page for precedence details.

1993 2801

2802Use `[features]` in `requirements.toml` to pin feature flags by the same

2803canonical keys that `config.toml` uses. Omitted keys remain unconstrained.

2804

1994| Key | Type / Values | Details |2805| Key | Type / Values | Details |

1995| --- | --- | --- |2806| --- | --- | --- |

1998| `allowed_web_search_modes` | `array<string>` | Allowed values for `web_search` (`disabled`, `cached`, `live`). `disabled` is always allowed; an empty list effectively allows only `disabled`. |2809| `allowed_web_search_modes` | `array<string>` | Allowed values for `web_search` (`disabled`, `cached`, `live`). `disabled` is always allowed; an empty list effectively allows only `disabled`. |

2810| `features` | `table` | Pinned feature values keyed by the canonical names from `config.toml`'s `[features]` table. |

2811| `features.<name>` | `boolean` | Require a specific canonical feature key to stay enabled or disabled. |

1999| `mcp_servers` | `table` | Allowlist of MCP servers that may be enabled. Both the server name (`<id>`) and its identity must match for the MCP server to be enabled. Any configured MCP server not in the allowlist (or with a mismatched identity) is disabled. |2812| `mcp_servers` | `table` | Allowlist of MCP servers that may be enabled. Both the server name (`<id>`) and its identity must match for the MCP server to be enabled. Any configured MCP server not in the allowlist (or with a mismatched identity) is disabled. |

2018 2831

2019Details2832Details

2020 2833

2021Allowed values for `approval\_policy`.2834Allowed values for `approval_policy` (for example `untrusted`, `on-request`, `never`, and `reject`).

2022 2835

2023Key2836Key

2024 2837

2046 2859

2047Key2860Key

2048 2861

2862`features`

2863

2864Type / Values

2865

2866`table`

2867

2868Details

2869

2870Pinned feature values keyed by the canonical names from `config.toml`'s `[features]` table.

2871

2872Key

2873

2874`features.<name>`

2875

2876Type / Values

2877

2878`boolean`

2879

2880Details

2881

2882Require a specific canonical feature key to stay enabled or disabled.

2883

2884Key

2885

2049`mcp_servers`2886`mcp_servers`

2050 2887

2051Type / Values2888Type / Values

config-sample.md +188 −107

Details

1# Sample Configuration1# Sample Configuration

2 2

~~3Use this example configuration as a starting point. It includes most keys Codex reads from `config.toml`, along with defaults and short notes.~~3Use this example configuration as a starting point. It includes most keys Codex reads from `config.toml`, along with default behaviors, recommended values where helpful, and short notes.

4 4

5For explanations and guidance, see:5For explanations and guidance, see:

6 6

7- [Config basics](https://developers.openai.com/codex/config-basic)7- [Config basics](https://developers.openai.com/codex/config-basic)

8- [Advanced Config](https://developers.openai.com/codex/config-advanced)8- [Advanced Config](https://developers.openai.com/codex/config-advanced)

9- [Config Reference](https://developers.openai.com/codex/config-reference)9- [Config Reference](https://developers.openai.com/codex/config-reference)

10- [Sandbox and approvals](https://developers.openai.com/codex/agent-approvals-security#sandbox-and-approvals)

11- [Managed configuration](https://developers.openai.com/codex/enterprise/managed-configuration)

10 12

11Use the snippet below as a reference. Copy only the keys and sections you need into `~/.codex/config.toml` (or into a project-scoped `.codex/config.toml`), then adjust values for your setup.13Use the snippet below as a reference. Copy only the keys and sections you need into `~/.codex/config.toml` (or into a project-scoped `.codex/config.toml`), then adjust values for your setup.

12 14

13```toml15```toml

14# Codex example configuration (config.toml)16# Codex example configuration (config.toml)

15#17#

~~16# This file lists all keys Codex reads from config.toml, their default values,~~18# This file lists the main keys Codex reads from config.toml, along with default

~~17# and concise explanations. Values here mirror the effective defaults compiled~~19# behaviors, recommended examples, and concise explanations. Adjust as needed.

~~18# into the CLI. Adjust as needed.~~

19#20#

20# Notes21# Notes

21# - Root keys must appear before tables in TOML.22# - Root keys must appear before tables in TOML.

26# Core Model Selection27# Core Model Selection

27################################################################################28################################################################################

28 29

~~29# Primary model used by Codex. Default: "gpt-5.2-codex" on all platforms.~~30# Primary model used by Codex. Recommended example for most users: "gpt-5.4".

~~30model = "gpt-5.2-codex"~~31model = "gpt-5.4"

31 32

~~32# Default communication style for supported models. Default: "friendly".~~33# Communication style for supported models. Allowed values: none | friendly | pragmatic

~~33# Allowed values: none | friendly | pragmatic~~34# personality = "pragmatic"

~~34# personality = "friendly"~~

35 35

36# Optional model override for /review. Default: unset (uses current session model).36# Optional model override for /review. Default: unset (uses current session model).

~~37# review_model = "gpt-5.2-codex"~~37# review_model = "gpt-5.4"

38 38

39# Provider id selected from [model_providers]. Default: "openai".39# Provider id selected from [model_providers]. Default: "openai".

40model_provider = "openai"40model_provider = "openai"

42# Default OSS provider for --oss sessions. When unset, Codex prompts. Default: unset.42# Default OSS provider for --oss sessions. When unset, Codex prompts. Default: unset.

43# oss_provider = "ollama"43# oss_provider = "ollama"

44 44

~~45# Optional manual model metadata. When unset, Codex auto-detects from model.~~45# Preferred service tier. `fast` is honored only when enabled in [features].

~~46# Uncomment to force values.~~46# service_tier = "flex" # fast | flex

48# Optional manual model metadata. When unset, Codex uses model or preset defaults.

47# model_context_window = 128000 # tokens; default: auto for model49# model_context_window = 128000 # tokens; default: auto for model

~~48# model_auto_compact_token_limit = 0 # tokens; unset uses model defaults~~50# model_auto_compact_token_limit = 64000 # tokens; unset uses model defaults

~~49# tool_output_token_limit = 10000 # tokens stored per tool output; default: 10000 for gpt-5.2-codex~~51# tool_output_token_limit = 12000 # tokens stored per tool output

52# model_catalog_json = "/absolute/path/to/models.json" # optional startup-only model catalog override

53# background_terminal_max_timeout = 300000 # ms; max empty write_stdin poll window (default 5m)

50# log_dir = "/absolute/path/to/codex-logs" # directory for Codex logs; default: "$CODEX_HOME/log"54# log_dir = "/absolute/path/to/codex-logs" # directory for Codex logs; default: "$CODEX_HOME/log"

55# sqlite_home = "/absolute/path/to/codex-state" # optional SQLite-backed runtime state directory

51 56

52################################################################################57################################################################################

53# Reasoning & Verbosity (Responses API capable models)58# Reasoning & Verbosity (Responses API capable models)

54################################################################################59################################################################################

55 60

~~57model_reasoning_effort = "medium"~~62# model_reasoning_effort = "medium"

65# plan_mode_reasoning_effort = "high"

58 66

60# model_reasoning_summary = "auto"68# model_reasoning_summary = "auto"

61 69

~~62# Text verbosity for GPT-5 family (Responses API): low | medium | high (default: medium)~~70# Text verbosity for GPT-5 family (Responses API): low | medium | high

63# model_verbosity = "medium"71# model_verbosity = "medium"

64 72

~~65# Force enable or disable reasoning summaries for current model~~73# Force enable or disable reasoning summaries for current model.

66# model_supports_reasoning_summaries = true74# model_supports_reasoning_summaries = true

67 75

68################################################################################76################################################################################

72# Additional user instructions are injected before AGENTS.md. Default: unset.80# Additional user instructions are injected before AGENTS.md. Default: unset.

73# developer_instructions = ""81# developer_instructions = ""

74 82

~~75# (Ignored) Optional legacy base instructions override (prefer AGENTS.md). Default: unset.~~

~~76# instructions = ""~~

78# Inline override for the history compaction prompt. Default: unset.83# Inline override for the history compaction prompt. Default: unset.

79# compact_prompt = ""84# compact_prompt = ""

80 85

86# Override the default commit co-author trailer. Set to "" to disable it.

87# commit_attribution = "Jane Doe <jane@example.com>"

81# Override built-in base instructions with a file path. Default: unset.89# Override built-in base instructions with a file path. Default: unset.

82# model_instructions_file = "/absolute/or/relative/path/to/instructions.txt"90# model_instructions_file = "/absolute/or/relative/path/to/instructions.txt"

83 91

~~84# Migration note: experimental_instructions_file was renamed to model_instructions_file (deprecated).~~

86# Load the compact prompt override from a file. Default: unset.92# Load the compact prompt override from a file. Default: unset.

87# experimental_compact_prompt_file = "/absolute/or/relative/path/to/compact_prompt.txt"93# experimental_compact_prompt_file = "/absolute/or/relative/path/to/compact_prompt.txt"

88 94

~~89# Legacy name for apply_patch_freeform. Default: false~~

~~90include_apply_patch_tool = false~~

92################################################################################95################################################################################

93# Notifications96# Notifications

94################################################################################97################################################################################

95 98

96# External notifier program (argv array). When unset: disabled.99# External notifier program (argv array). When unset: disabled.

~~97# Example: notify = ["notify-send", "Codex"]~~100# notify = ["notify-send", "Codex"]

~~98notify = [ ]~~

99 101

100################################################################################102################################################################################

101# Approval & Sandbox103# Approval & Sandbox

105# - untrusted: only known-safe read-only commands auto-run; others prompt107# - untrusted: only known-safe read-only commands auto-run; others prompt

106# - on-request: model decides when to ask (default)108# - on-request: model decides when to ask (default)

107# - never: never prompt (risky)109# - never: never prompt (risky)

110# - { reject = { ... } }: auto-reject selected prompt categories

108approval_policy = "on-request"111approval_policy = "on-request"

112# Example granular auto-reject policy:

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

114

115# Allow login-shell semantics for shell-based tools when they request `login = true`.

116# Default: true. Set false to force non-login shells and reject explicit login-shell requests.

117allow_login_shell = true

109 118

110# Filesystem/network sandbox policy for tool calls:119# Filesystem/network sandbox policy for tool calls:

111# - read-only (default)120# - read-only (default)

120# Where to persist CLI login credentials: file (default) | keyring | auto129# Where to persist CLI login credentials: file (default) | keyring | auto

121cli_auth_credentials_store = "file"130cli_auth_credentials_store = "file"

122 131

123# Base URL for ChatGPT auth flow (not OpenAI API). Default:132# Base URL for ChatGPT auth flow (not OpenAI API).

124chatgpt_base_url = "https://chatgpt.com/backend-api/"133chatgpt_base_url = "https://chatgpt.com/backend-api/"

125 134

126# Restrict ChatGPT login to a specific workspace id. Default: unset.135# Restrict ChatGPT login to a specific workspace id. Default: unset.

127# forced_chatgpt_workspace_id = ""136# forced_chatgpt_workspace_id = "00000000-0000-0000-0000-000000000000"

128 137

129# Force login mechanism when Codex would normally auto-select. Default: unset.138# Force login mechanism when Codex would normally auto-select. Default: unset.

130# Allowed values: chatgpt | api139# Allowed values: chatgpt | api

132 141

133# Preferred store for MCP OAuth credentials: auto (default) | file | keyring142# Preferred store for MCP OAuth credentials: auto (default) | file | keyring

134mcp_oauth_credentials_store = "auto"143mcp_oauth_credentials_store = "auto"

~~135~~

136# Optional fixed port for MCP OAuth callback: 1-65535. Default: unset.144# Optional fixed port for MCP OAuth callback: 1-65535. Default: unset.

137# mcp_oauth_callback_port = 4321145# mcp_oauth_callback_port = 4321

146# Optional redirect URI override for MCP OAuth login (for example, remote devbox ingress).

147# Custom callback paths are supported. `mcp_oauth_callback_port` still controls the listener port.

148# mcp_oauth_callback_url = "https://devbox.example.internal/callback"

138 149

139################################################################################150################################################################################

140# Project Documentation Controls151# Project Documentation Controls

185# If you use --yolo or another full access sandbox setting, web search defaults to live.196# If you use --yolo or another full access sandbox setting, web search defaults to live.

186web_search = "cached"197web_search = "cached"

187 198

199# Active profile name. When unset, no profile is applied.

200# profile = "default"

201

202# Suppress the warning shown when under-development feature flags are enabled.

203# suppress_unstable_features_warning = true

204

188################################################################################205################################################################################

189# Profiles (named presets)206# Agents (multi-agent roles and limits)

190################################################################################207################################################################################

191 208

192# Active profile name. When unset, no profile is applied.209[agents]

193# profile = "default"210# Maximum concurrently open agent threads. Default: 6

211# max_threads = 6

212# Maximum nested spawn depth. Root session starts at depth 0. Default: 1

213# max_depth = 1

214# Default timeout per worker for spawn_agents_on_csv jobs. When unset, the tool defaults to 1800 seconds.

215# job_max_runtime_seconds = 1800

216

217# [agents.reviewer]

218# description = "Find correctness, security, and test risks in code."

219# config_file = "./agents/reviewer.toml" # relative to the config.toml that defines it

220# nickname_candidates = ["Athena", "Ada"]

194 221

195################################################################################222################################################################################

196# Skills (per-skill overrides)223# Skills (per-skill overrides)

198 225

199# Disable or re-enable a specific skill without deleting it.226# Disable or re-enable a specific skill without deleting it.

200[[skills.config]]227[[skills.config]]

201# path = "/path/to/skill"228# path = "/path/to/skill/SKILL.md"

202# enabled = false229# enabled = false

203 230

204################################################################################

205# Experimental toggles (legacy; prefer [features])

206################################################################################

~~207~~

208experimental_use_unified_exec_tool = false

~~209~~

210# Include apply_patch via freeform editing path (affects default tool set). Default: false

211experimental_use_freeform_apply_patch = false

~~212~~

213################################################################################231################################################################################

214# Sandbox settings (tables)232# Sandbox settings (tables)

215################################################################################233################################################################################

232[shell_environment_policy]250[shell_environment_policy]

233# inherit: all (default) | core | none251# inherit: all (default) | core | none

234inherit = "all"252inherit = "all"

235# Skip default excludes for names containing KEY/SECRET/TOKEN (case-insensitive). Default: true253# Skip default excludes for names containing KEY/SECRET/TOKEN (case-insensitive). Default: false

236ignore_default_excludes = true254ignore_default_excludes = false

237# Case-insensitive glob patterns to remove (e.g., "AWS_*", "AZURE_*"). Default: []255# Case-insensitive glob patterns to remove (e.g., "AWS_*", "AZURE_*"). Default: []

238exclude = []256exclude = []

239# Explicit key/value overrides (always win). Default: {}257# Explicit key/value overrides (always win). Default: {}

243# Experimental: run via user shell profile. Default: false261# Experimental: run via user shell profile. Default: false

244experimental_use_profile = false262experimental_use_profile = false

245 263

264################################################################################

265# Managed network proxy settings

266################################################################################

267

268[permissions.network]

269# enabled = true

270# proxy_url = "http://127.0.0.1:43128"

271# admin_url = "http://127.0.0.1:43129"

272# enable_socks5 = false

273# socks_url = "http://127.0.0.1:43130"

274# enable_socks5_udp = false

275# allow_upstream_proxy = false

276# dangerously_allow_non_loopback_proxy = false

277# dangerously_allow_non_loopback_admin = false

278# dangerously_allow_all_unix_sockets = false

279# mode = "limited" # limited | full

280# allowed_domains = ["api.openai.com"]

281# denied_domains = ["example.com"]

282# allow_unix_sockets = ["/var/run/docker.sock"]

283# allow_local_binding = false

284

246################################################################################285################################################################################

247# History (table)286# History (table)

248################################################################################287################################################################################

251# save-all (default) | none290# save-all (default) | none

252persistence = "save-all"291persistence = "save-all"

253# Maximum bytes for history file; oldest entries are trimmed when exceeded. Example: 5242880292# Maximum bytes for history file; oldest entries are trimmed when exceeded. Example: 5242880

254# max_bytes = 0293# max_bytes = 5242880

255 294

256################################################################################295################################################################################

257# UI, Notifications, and Misc (tables)296# UI, Notifications, and Misc (tables)

274# Control alternate screen usage (auto skips it in Zellij to preserve scrollback).313# Control alternate screen usage (auto skips it in Zellij to preserve scrollback).

275# alternate_screen = "auto"314# alternate_screen = "auto"

276 315

277# Ordered list of footer status-line item IDs. Default: null (disabled).316# Ordered list of footer status-line item IDs. When unset, Codex uses:

317# ["model-with-reasoning", "context-remaining", "current-dir"].

318# Set to [] to hide the footer.

278# status_line = ["model", "context-remaining", "git-branch"]319# status_line = ["model", "context-remaining", "git-branch"]

279 320

321# Syntax-highlighting theme (kebab-case). Use /theme in the TUI to preview and save.

322# You can also add custom .tmTheme files under $CODEX_HOME/themes.

323# theme = "catppuccin-mocha"

324

325# Internal tooltip state keyed by model slug. Usually managed by Codex.

326# [tui.model_availability_nux]

327# "gpt-5.4" = 1

328

329# Enable or disable analytics for this machine. When unset, Codex uses its default behavior.

330[analytics]

331enabled = true

332

280# Control whether users can submit feedback from `/feedback`. Default: true333# Control whether users can submit feedback from `/feedback`. Default: true

281[feedback]334[feedback]

282enabled = true335enabled = true

290# "hide_gpt-5.1-codex-max_migration_prompt" = true343# "hide_gpt-5.1-codex-max_migration_prompt" = true

291# model_migrations = { "gpt-4.1" = "gpt-5.1" }344# model_migrations = { "gpt-4.1" = "gpt-5.1" }

292 345

293# Suppress the warning shown when under-development feature flags are enabled.

294# suppress_unstable_features_warning = true

~~295~~

296################################################################################346################################################################################

297# Centralized Feature Flags (preferred)347# Centralized Feature Flags (preferred)

298################################################################################348################################################################################

299 349

300[features]350[features]

301# Leave this table empty to accept defaults. Set explicit booleans to opt in/out.351# Leave this table empty to accept defaults. Set explicit booleans to opt in/out.

302shell_tool = true352# shell_tool = true

303# apps = false353# apps = false

304# apps_mcp_gateway = false354# apps_mcp_gateway = false

305# Deprecated legacy toggles; prefer the top-level `web_search` setting.355# unified_exec = false

306# web_search = false356# shell_snapshot = false

307# web_search_cached = false357# multi_agent = false

308# web_search_request = false

309unified_exec = false

310shell_snapshot = false

311apply_patch_freeform = false

312# search_tool = false

313# personality = true358# personality = true

314request_rule = true359# use_linux_sandbox_bwrap = false

315collaboration_modes = true360# runtime_metrics = true

316use_linux_sandbox_bwrap = false361# powershell_utf8 = true

317experimental_windows_sandbox = false362# child_agents_md = false

318elevated_windows_sandbox = false363# sqlite = true

319remote_models = false364# fast_mode = true

320runtime_metrics = false365# enable_request_compression = true

321powershell_utf8 = true366# image_generation = false

322child_agents_md = false367# skill_mcp_dependency_install = true

368# skill_env_var_dependency_prompt = false

369# default_mode_request_user_input = false

370# artifact = false

371# prevent_idle_sleep = false

372# responses_websockets = false

373# responses_websockets_v2 = false

374# image_detail_original = false

323 375

324################################################################################376################################################################################

325# Define MCP servers under this table. Leave empty to disable.377# Define MCP servers under this table. Leave empty to disable.

341# tool_timeout_sec = 60.0 # optional; default 60.0 seconds393# tool_timeout_sec = 60.0 # optional; default 60.0 seconds

342# enabled_tools = ["search", "summarize"] # optional allow-list394# enabled_tools = ["search", "summarize"] # optional allow-list

343# disabled_tools = ["slow-tool"] # optional deny-list (applied after allow-list)395# disabled_tools = ["slow-tool"] # optional deny-list (applied after allow-list)

396# scopes = ["read:docs"] # optional OAuth scopes

397# oauth_resource = "https://docs.example.com/" # optional OAuth resource

344 398

345# --- Example: Streamable HTTP transport ---399# --- Example: Streamable HTTP transport ---

346# [mcp_servers.github]400# [mcp_servers.github]

353# startup_timeout_sec = 10.0 # optional407# startup_timeout_sec = 10.0 # optional

354# tool_timeout_sec = 60.0 # optional408# tool_timeout_sec = 60.0 # optional

355# enabled_tools = ["list_issues"] # optional allow-list409# enabled_tools = ["list_issues"] # optional allow-list

410# disabled_tools = ["delete_issue"] # optional deny-list

411# scopes = ["repo"] # optional OAuth scopes

356 412

357################################################################################413################################################################################

358# Model Providers414# Model Providers

359################################################################################415################################################################################

360 416

361# Built-ins include:417# Built-ins include:

362# - openai (Responses API; requires login or OPENAI_API_KEY via auth flow)418# - openai

363# - oss (Chat Completions API; defaults to http://localhost:11434/v1)419# - ollama

420# - lmstudio

364 421

365[model_providers]422[model_providers]

366 423

368# [model_providers.openaidr]425# [model_providers.openaidr]

369# name = "OpenAI Data Residency"426# name = "OpenAI Data Residency"

370# base_url = "https://us.api.openai.com/v1" # example with 'us' domain prefix427# base_url = "https://us.api.openai.com/v1" # example with 'us' domain prefix

371# wire_api = "responses" # "responses" | "chat" (default varies)428# wire_api = "responses" # only supported value

372# # requires_openai_auth = true # built-in OpenAI defaults to true429# # requires_openai_auth = true # built-in OpenAI defaults to true

373# # request_max_retries = 4 # default 4; max 100430# # request_max_retries = 4 # default 4; max 100

374# # stream_max_retries = 5 # default 5; max 100431# # stream_max_retries = 5 # default 5; max 100

375# # stream_idle_timeout_ms = 300000 # default 300_000 (5m)432# # stream_idle_timeout_ms = 300000 # default 300_000 (5m)

433# # supports_websockets = true # optional

376# # experimental_bearer_token = "sk-example" # optional dev-only direct bearer token434# # experimental_bearer_token = "sk-example" # optional dev-only direct bearer token

377# # http_headers = { "X-Example" = "value" }435# # http_headers = { "X-Example" = "value" }

378# # env_http_headers = { "OpenAI-Organization" = "OPENAI_ORGANIZATION", "OpenAI-Project" = "OPENAI_PROJECT" }436# # env_http_headers = { "OpenAI-Organization" = "OPENAI_ORGANIZATION", "OpenAI-Project" = "OPENAI_PROJECT" }

379 437

380# --- Example: Azure (Chat/Responses depending on endpoint) ---438# --- Example: Azure/OpenAI-compatible provider ---

381# [model_providers.azure]439# [model_providers.azure]

382# name = "Azure"440# name = "Azure"

383# base_url = "https://YOUR_PROJECT_NAME.openai.azure.com/openai"441# base_url = "https://YOUR_PROJECT_NAME.openai.azure.com/openai"

384# wire_api = "responses" # or "chat" per endpoint442# wire_api = "responses"

385# query_params = { api-version = "2025-04-01-preview" }443# query_params = { api-version = "2025-04-01-preview" }

386# env_key = "AZURE_OPENAI_API_KEY"444# env_key = "AZURE_OPENAI_API_KEY"

387# # env_key_instructions = "Set AZURE_OPENAI_API_KEY in your environment"445# env_key_instructions = "Set AZURE_OPENAI_API_KEY in your environment"

446# # supports_websockets = false

388 447

389# --- Example: Local OSS (e.g., Ollama-compatible) ---448# --- Example: Local OSS (e.g., Ollama-compatible) ---

390# [model_providers.ollama]449# [model_providers.ollama]

391# name = "Ollama"450# name = "Ollama"

392# base_url = "http://localhost:11434/v1"451# base_url = "http://localhost:11434/v1"

393# wire_api = "chat"452# wire_api = "responses"

453

454################################################################################

455# Apps / Connectors

456################################################################################

457

458# Optional per-app controls.

459[apps]

460# [_default] applies to all apps unless overridden per app.

461# [apps._default]

462# enabled = true

463# destructive_enabled = true

464# open_world_enabled = true

465#

466# [apps.google_drive]

467# enabled = false

468# destructive_enabled = false # block destructive-hint tools for this app

469# default_tools_enabled = true

470# default_tools_approval_mode = "prompt" # auto | prompt | approve

471#

472# [apps.google_drive.tools."files/delete"]

473# enabled = false

474# approval_mode = "approve"

394 475

395################################################################################476################################################################################

396# Profiles (named presets)477# Profiles (named presets)

399[profiles]480[profiles]

400 481

401# [profiles.default]482# [profiles.default]

402# model = "gpt-5.2-codex"483# model = "gpt-5.4"

403# model_provider = "openai"484# model_provider = "openai"

404# approval_policy = "on-request"485# approval_policy = "on-request"

405# sandbox_mode = "read-only"486# sandbox_mode = "read-only"

487# service_tier = "flex"

406# oss_provider = "ollama"488# oss_provider = "ollama"

407# model_reasoning_effort = "medium"489# model_reasoning_effort = "medium"

490# plan_mode_reasoning_effort = "high"

408# model_reasoning_summary = "auto"491# model_reasoning_summary = "auto"

409# model_verbosity = "medium"492# model_verbosity = "medium"

410# personality = "friendly" # or "pragmatic" or "none"493# personality = "pragmatic" # or "friendly" or "none"

411# chatgpt_base_url = "https://chatgpt.com/backend-api/"494# chatgpt_base_url = "https://chatgpt.com/backend-api/"

495# model_catalog_json = "./models.json"

496# model_instructions_file = "/absolute/or/relative/path/to/instructions.txt"

412# experimental_compact_prompt_file = "./compact_prompt.txt"497# experimental_compact_prompt_file = "./compact_prompt.txt"

413# include_apply_patch_tool = false498# tools_view_image = true

414# experimental_use_unified_exec_tool = false

415# experimental_use_freeform_apply_patch = false

416# tools.web_search = false # deprecated legacy alias; prefer top-level `web_search`

417# features = { unified_exec = false }499# features = { unified_exec = false }

418 500

419################################################################################

420# Apps / Connectors

421################################################################################

~~422~~

423# Optional per-app controls.

424[apps]

425# [apps.google_drive]

426# enabled = false

427# disabled_reason = "user" # or "unknown"

~~428~~

429################################################################################501################################################################################

430# Projects (trust levels)502# Projects (trust levels)

431################################################################################503################################################################################

432 504

433# Mark specific worktrees as trusted or untrusted.

434[projects]505[projects]

506# Mark specific worktrees as trusted or untrusted.

435# [projects."/absolute/path/to/project"]507# [projects."/absolute/path/to/project"]

436# trust_level = "trusted" # or "untrusted"508# trust_level = "trusted" # or "untrusted"

437 509

510################################################################################

511# Tools

512################################################################################

513

514[tools]

515# view_image = true

516

438################################################################################517################################################################################

439# OpenTelemetry (OTEL) - disabled by default518# OpenTelemetry (OTEL) - disabled by default

440################################################################################519################################################################################

448exporter = "none"527exporter = "none"

449# Trace exporter: none (default) | otlp-http | otlp-grpc528# Trace exporter: none (default) | otlp-http | otlp-grpc

450trace_exporter = "none"529trace_exporter = "none"

530# Metrics exporter: none | statsig | otlp-http | otlp-grpc

531metrics_exporter = "statsig"

451 532

452# Example OTLP/HTTP exporter configuration533# Example OTLP/HTTP exporter configuration

453# [otel.exporter."otlp-http"]534# [otel.exporter."otlp-http"]

457# [otel.exporter."otlp-http".headers]538# [otel.exporter."otlp-http".headers]

458# "x-otlp-api-key" = "${OTLP_TOKEN}"539# "x-otlp-api-key" = "${OTLP_TOKEN}"

459 540

460# Example OTLP/gRPC exporter configuration

461# [otel.exporter."otlp-grpc"]

462# endpoint = "https://otel.example.com:4317",

463# headers = { "x-otlp-meta" = "abc123" }

~~464~~

465# Example OTLP exporter with mutual TLS

466# [otel.exporter."otlp-http"]

467# endpoint = "https://otel.example.com/v1/logs"

468# protocol = "binary"

~~469~~

470# [otel.exporter."otlp-http".headers]

471# "x-otlp-api-key" = "${OTLP_TOKEN}"

~~472~~

473# [otel.exporter."otlp-http".tls]541# [otel.exporter."otlp-http".tls]

474# ca-certificate = "certs/otel-ca.pem"542# ca-certificate = "certs/otel-ca.pem"

475# client-certificate = "/etc/codex/certs/client.pem"543# client-certificate = "/etc/codex/certs/client.pem"

476# client-private-key = "/etc/codex/certs/client-key.pem"544# client-private-key = "/etc/codex/certs/client-key.pem"

545

546# Example OTLP/gRPC trace exporter configuration

547# [otel.trace_exporter."otlp-grpc"]

548# endpoint = "https://otel.example.com:4317"

549# headers = { "x-otlp-meta" = "abc123" }

550

551################################################################################

552# Windows

553################################################################################

554

555[windows]

556# Native Windows sandbox mode (Windows only): unelevated | elevated

557sandbox = "unelevated"

477```558```

enterprise/admin-setup.md +145 −85

Details

2 2

3This guide is for ChatGPT Enterprise admins who want to set up Codex for their workspace.3This guide is for ChatGPT Enterprise admins who want to set up Codex for their workspace.

4 4

5Use this page as the step-by-step rollout guide. It focuses on setup order and decision points. For detailed policy, configuration, and monitoring details, use the linked pages: [Authentication](https://developers.openai.com/codex/auth), [Agent approvals & security](https://developers.openai.com/codex/agent-approvals-security), [Managed configuration](https://developers.openai.com/codex/enterprise/managed-configuration), and [Governance](https://developers.openai.com/codex/enterprise/governance).

5## Enterprise-grade security and privacy7## Enterprise-grade security and privacy

6 8

7Codex supports ChatGPT Enterprise security features, including:9Codex supports ChatGPT Enterprise security features, including:

8 10

9- No training on enterprise data11- No training on enterprise data

~~10- Zero data retention for the CLI and IDE~~12- Zero data retention for the App, CLI, and IDE (code remains in developer environment)

~~11- Residency and retention follow ChatGPT Enterprise policies~~13- Residency and retention that follow ChatGPT Enterprise policies

12- Granular user access controls14- Granular user access controls

~~13- Data encryption at rest (AES 256) and in transit (TLS 1.2+)~~15- Data encryption at rest (AES-256) and in transit (TLS 1.2+)

14 16

~~15For more, see [Security](https://developers.openai.com/codex/security).~~17For security controls and runtime protections, see [Agent approvals & security](https://developers.openai.com/codex/agent-approvals-security). Refer to [Zero Data Retention (ZDR)](https://platform.openai.com/docs/guides/your-data#zero-data-retention) for more details.

16 18

17## Local vs. cloud setup19## Local vs. cloud setup

18 20

19Codex operates in two environments: local and cloud.21Codex operates in two environments: local and cloud.

20 22

~~211. Local use includes the Codex app, CLI, and IDE extension. The agent runs on the developer’s computer in a sandbox.~~231. **Codex local** includes the Codex app, CLI, and IDE extension. The agent runs on the developer’s computer in a sandbox.

222. Use in the cloud includes Codex cloud, iOS, Code Review, and tasks created by the [Slack integration](https://developers.openai.com/codex/integrations/slack). The agent runs remotely in a hosted container with your codebase.242. **Codex cloud** includes hosted Codex features (including Codex cloud, iOS, Code Review, and tasks created by the [Slack integration](https://developers.openai.com/codex/integrations/slack) or [Linear integration](https://developers.openai.com/codex/integrations/linear)). The agent runs remotely in a hosted container with your codebase.

23 25

~~24Use separate permissions and role-based access control (RBAC) to control access to local and cloud features. You can enable local, cloud, or both for all users or for specific groups.~~26You can enable local, cloud, or both, and control access with workspace settings and role-based access control (RBAC).

25 27

~~26## Codex local setup~~28## Step 0: Owners and rollout decision

27 29

~~28### Enable Codex app, CLI, and IDE extension in workspace settings~~30Ensure you have the following owners:

29 31

30To enable Codex locally for workspace members, go to [Workspace Settings > Settings and Permissions](https://chatgpt.com/admin/settings). Turn on **Allow members to use Codex Local**. This setting doesn’t require the GitHub connector.32- Workspace owner with access to ChatGPT Enterprise

33- IT management owner for managed configuration

34- Governance owner for analytics / compliance review

31 35

32After you turn this on, users can sign in to use the Codex app, CLI, and IDE extension with their ChatGPT account. If you turn off this setting, users who attempt to use the Codex app, CLI, or IDE will see the following error: “403 - Unauthorized. Contact your ChatGPT administrator for access.”36A rollout decision:

33 37

~~34## Team Config~~38- Codex local only (Codex app, CLI, and IDE extension)

39- Codex cloud only (Codex web, GitHub code review)

40- Both local + cloud

35 41

~~36Teams who want to standardize Codex across an organization can use Team Config to share defaults, rules, and skills without duplicating setup on every local configuration.~~42Review [authentication](https://developers.openai.com/codex/auth) before rollout:

37 43

~~38| Type | Path | Use it to |~~44- Codex local supports ChatGPT sign-in or API keys. Confirm MFA/SSO requirements and any managed login restrictions in authentication

~~39| ------------------------------------ | ------------- | ---------------------------------------------------------------------------- |~~45- Codex cloud requires ChatGPT sign-in

~~40| [Config basics](https://developers.openai.com/codex/config-basic) | `config.toml` | Set defaults for sandbox mode, approvals, model, reasoning effort, and more. |~~

~~41| [Rules](https://developers.openai.com/codex/rules) | `rules/` | Control which commands Codex can run outside the sandbox. |~~

~~42| [Skills](https://developers.openai.com/codex/skills) | `skills/` | Make shared skills available to your team. |~~

43 46

~~44For locations and precedence, see [Config basics](https://developers.openai.com/codex/config-basic#configuration-precedence).~~47## Step 1: Enable workspace toggles

49Turn on only the Codex features you plan to roll out in this phase.

51Go to [Workspace Settings > Settings and Permissions](https://chatgpt.com/admin/settings).

53### Codex local

55Turn on **Allow members to use Codex Local**.

57This enables use of the Codex app, CLI, and IDE extension for allowed users.

45 58

~~46## Codex cloud setup~~59If this toggle is off, users who attempt to use the Codex app, CLI, or IDE will see the following error: “403 - Unauthorized. Contact your ChatGPT administrator for access.”

61#### Enable device code authentication for Codex CLI

63Allow developers to sign in with device codes when using Codex CLI in a non-interactive environment. More details in [authentication](https://developers.openai.com/codex/auth/).

65![Codex local toggle](/images/codex/enterprise/local-toggle-config.png)

67### Codex cloud

47 68

48### Prerequisites69### Prerequisites

49 70

57 78

58Start by turning on the ChatGPT GitHub Connector in the Codex section of [Workspace Settings > Settings and Permissions](https://chatgpt.com/admin/settings).79Start by turning on the ChatGPT GitHub Connector in the Codex section of [Workspace Settings > Settings and Permissions](https://chatgpt.com/admin/settings).

59 80

~~60To enable Codex cloud for your workspace, turn on **Allow members to use Codex cloud**.~~81To enable Codex cloud for your workspace, turn on **Allow members to use Codex cloud**. Once enabled, users can access Codex directly from the left-hand navigation panel in ChatGPT.

83Note that it may take up to 10 minutes for Codex to appear in ChatGPT.

85#### Allow members to administer Codex

87Allows users to view overall Codex [workspace analytics](https://chatgpt.com/codex/settings/analytics), access [cloud-managed requirements](https://chatgpt.com/codex/settings/managed-configs), and manage Cloud environments (edit and delete).

89Codex cloud not required.

91#### Enable Codex Slack app to post answers on task completion

93Codex posts its full answer back to Slack when the task completes. Otherwise, Codex posts only a link to the task.

95To learn more, see [Codex in Slack](https://developers.openai.com/codex/integrations/slack).

97#### Enable Codex agent to access the internet

99By default, Codex cloud agents have no internet access during runtime to help protect against security and safety risks like prompt injection.

100

101This setting enables users to use an allowlist for common software dependency domains, add more domains and trusted sites, and specify allowed HTTP methods.

61 102

~~62Once enabled, users can access Codex directly from the left-hand navigation panel in ChatGPT.~~103For security implications of internet access and runtime controls, see [Agent approvals & security](https://developers.openai.com/codex/agent-approvals-security).

63 104

64![Codex cloud toggle](/images/codex/enterprise/cloud-toggle-config.png)105![Codex cloud toggle](/images/codex/enterprise/cloud-toggle-config.png)

65 106

~~66After you turn on Codex in your Enterprise workspace settings, it may take up~~107## Step 2: Set up custom roles (RBAC)

~~67to 10 minutes for Codex to appear in ChatGPT.~~

68 108

~~69### Configure the GitHub Connector IP allow list~~109Use RBAC to control which users or groups can access Codex local and Codex cloud.

70 110

~~71To control which IP addresses can connect to your ChatGPT GitHub connector, configure these IP ranges:~~111### What RBAC lets you do

72 112

~~73- [ChatGPT egress IP ranges](https://openai.com/chatgpt-actions.json)~~113Workspace Owners can use RBAC in ChatGPT admin settings to:

~~74- [Codex container egress IP ranges](https://openai.com/chatgpt-agents.json)~~

75 114

~~76These IP ranges can change. Consider checking them automatically and updating your allow list based on the latest values.~~115- Set a default role for users who are not assigned any custom role

116- Create custom roles with granular permissions

117- Assign one or more custom roles to Groups (including SCIM-synced groups)

118- Manage roles centrally from the Custom Roles tab

77 119

~~78### Allow members to administer Codex~~120Users can inherit multiple roles, and permissions resolve to the maximum allowed across those roles.

79 121

~~80This toggle allows users to view Codex workspace analytics and manage environments (edit and delete).~~122### Important behavior to plan for

81 123

~~82Codex supports role-based access (see [Role-based access (RBAC)](#role-based-access-rbac)), so you can turn on this toggle for a specific subset of users.~~124Users in any custom role group do not use the workspace default permissions.

83 125

~~84### Enable Codex Slack app to post answers on task completion~~126If you are gradually rolling out Codex, one suggestion is to have a “Codex Users” group and a second “Codex Admin” group that has the “Allow members to administer Codex” toggle enabled.

85 127

~~86Codex integrates with Slack. When a user mentions `@Codex` in Slack, Codex starts a cloud task, gets context from the Slack thread, and responds with a link to a PR to review in the thread.~~128For RBAC setup details and the full permission model, see the [OpenAI RBAC Help Center article](https://help.openai.com/en/articles/11750701-rbac).

87 129

88To allow the Slack app to post answers on task completion, turn on **Allow Codex Slack app to post answers on task completion**. When enabled, Codex posts its full answer back to Slack when the task completes. Otherwise, Codex posts only a link to the task.130## Step 3: Configure Codex local managed settings

89 131

~~90To learn more, see [Codex in Slack](https://developers.openai.com/codex/integrations/slack).~~132For Codex local, set an admin-approved baseline for local behavior before broader rollout.

91 133

~~92### Enable Codex agent to access the internet~~134### Use managed configuration for two different goals

93 135

~~94By default, Codex cloud agents have no internet access during runtime to help protect against security and safety risks like prompt injection.~~136- **Requirements** (`requirements.toml`): Admin-enforced constraints users cannot override

137- **Managed defaults** (`managed_config.toml`): Starting values applied when Codex launches

95 138

~~96As an admin, you can allow users to enable agent internet access in their environments. To enable it, turn on **Allow Codex agent to access the internet**.~~139### Team Config

97 140

~~98When this setting is on, users can use an allow list for common software dependency domains, add more domains and trusted sites, and specify allowed HTTP methods.~~141Teams who want to standardize Codex across an organization can use Team Config to share defaults, rules, and skills without duplicating setup on every local configuration.

99 142

100### Enable code review with Codex cloud143| Type | Path | Use it to |

144| ------------------------------------ | ------------- | ---------------------------------------------------------------------------- |

145| [Config basics](https://developers.openai.com/codex/config-basic) | `config.toml` | Set defaults for sandbox mode, approvals, model, reasoning effort, and more. |

146| [Rules](https://developers.openai.com/codex/rules) | `rules/` | Control which commands Codex can run outside the sandbox. |

147| [Skills](https://developers.openai.com/codex/skills) | `skills/` | Make shared skills available to your team. |

148

149For locations and precedence, see [Config basics](https://developers.openai.com/codex/config-basic#configuration-precedence).

150

151### Recommended first decisions for local rollout

152

153Define a baseline for your pilot:

154

155- Approval policy posture

156- Sandbox mode posture

157- Web search posture

158- MCP / connectors policy

159- Local logging and telemetry posture

101 160

102To allow Codex to do code reviews, go to [Settings → Code review](https://chatgpt.com/codex/settings/code-review).161For exact keys, precedence, MDM deployment, and examples, see [Managed configuration](https://developers.openai.com/codex/enterprise/managed-configuration) and [Agent approvals & security](https://developers.openai.com/codex/agent-approvals-security).

103 162

104Users can specify whether they want Codex to review their pull requests. Users can also configure whether code review runs for all contributors to a repository.163If you plan to restrict login method or workspace for local clients, see the admin-managed authentication restrictions in [Authentication](https://developers.openai.com/codex/auth).

105 164

106Codex supports two types of code reviews:165## Step 4: Configure Codex cloud usage (if enabled)

107 166

1081. Automatically triggered code reviews when a user opens a PR for review.167This step covers repository and environment setup after the Codex cloud workspace toggle is enabled.

1092. Reactive code reviews when a user mentions @Codex to look at issues. For example, “@Codex fix this CI error” or “@Codex address that feedback.”

110 168

111## Role-based access (RBAC)169### Connect Codex cloud to repositories

112 170

113Codex supports role-based access. RBAC is a security and permissions model used to control access to systems or resources based on a user’s role assignments.1711. Navigate to [Codex](https://chatgpt.com/codex) and select **Get started**

1722. Select **Connect to GitHub** to install the ChatGPT GitHub Connector if you haven't already connected GitHub to ChatGPT

1733. Install or authorize the ChatGPT GitHub Connector

1744. Choose an installation target for the ChatGPT Connector (typically your main organization)

1755. Allow the repositories you want to connect to Codex

114 176

115To enable RBAC for Codex, navigate to Settings & Permissions → Custom Roles in [ChatGPT’s admin page](https://chatgpt.com/admin/settings) and assign roles to groups created in the Groups tab.177For more, see [Cloud environments](https://developers.openai.com/codex/cloud/environments).

116 178

117This simplifies permission management for Codex and improves security in your ChatGPT workspace. To learn more, see the [Help Center article](https://help.openai.com/en/articles/11750701-rbac).179Codex uses short-lived, least-privilege GitHub App installation tokens for each operation and respects the user's existing GitHub repository permissions and branch protection rules.

180

181### Configure IP addresses (as needed)

182

183Configure connector / IP allow lists if required by your network policy with these [egress IP ranges](https://openai.com/chatgpt-agents.json).

184

185These IP ranges can change. Consider checking them automatically and updating your allow list based on the latest values.

186

187### Enable code review with Codex cloud

118 188

119## Set up your first Codex cloud environment189To allow Codex to perform code reviews on GitHub, go to [Settings → Code review](https://chatgpt.com/codex/settings/code-review).

120 190

1211. Go to Codex cloud and select **Get started**.191Code review can be configured at the repository level. Users can also enable auto review for their PRs and choose when Codex automatically triggers a review. More details on [GitHub](https://developers.openai.com/codex/integrations/github) integration page.

1222. Select **Connect to GitHub** to install the ChatGPT GitHub Connector if you haven’t already connected GitHub to ChatGPT.

123 - Allow the ChatGPT Connector for your account.

124 - Choose an installation target for the ChatGPT Connector (typically your main organization).

125 - Allow the repositories you want to connect to Codex (a GitHub admin may need to approve this).

1263. Create your first environment by selecting the repository most relevant to your developers, then select **Create environment**.

127 - Add the email addresses of any environment collaborators to give them edit access.

1284. Start a few starter tasks (for example, writing tests, fixing bugs, or exploring code).

129 192

130You have now created your first environment. Users who connect to GitHub can create tasks using this environment. Users who have access to the repository can also push pull requests generated from their tasks.193Additional integration docs for [Slack](https://developers.openai.com/codex/integrations/slack), [GitHub](https://developers.openai.com/codex/integrations/github), and [Linear](https://developers.openai.com/codex/integrations/linear).

131 194

132### Environment management195## Step 5: Set up governance and observability

133 196

134As a ChatGPT workspace administrator, you can edit and delete Codex environments in your workspace.197Codex gives enterprise teams several options for visibility into adoption and impact. Set up governance early so your team can monitor adoption, investigate issues, and support compliance workflows.

135 198

136### Connect more GitHub repositories with Codex cloud199### Codex governance typically uses

137 200

1381. Select **Environments**, or open the environment selector and select **Manage Environments**.201- Analytics Dashboard for quick, self-serve visibility

1392. Select **Create Environment**.202- Analytics API for programmatic reporting and BI integration

1403. Select the repository you want to connect.203- Compliance API for audit and investigation workflows

1414. Enter a name and description.

1425. Select the environment visibility.

1436. Select **Create Environment**.

144 204

145Codex automatically optimizes your environment setup by reviewing your codebase. Avoid advanced environment configuration until you observe specific performance issues. For more, see [Codex cloud](https://developers.openai.com/codex/cloud).205### Recommended minimum setup

146 206

147### Share setup instructions with users207- Assign an owner for adoption reporting

208- Assign an owner for audit and compliance review

209- Define a review cadence

210- Decide what success looks like

148 211

149You can share these steps with end users:212For details and examples, see [Governance](https://developers.openai.com/codex/enterprise/governance).

150 213

1511. Go to [Codex](https://chatgpt.com/codex) in the left-hand panel of ChatGPT.214## Step 6: Confirm and validate setup

1522. Select **Connect to GitHub** in the prompt composer if you’re not already connected.

153 - Sign in to GitHub.

1543. You can now use shared environments with your workspace or create your own environment.

1554. Try a task in both Ask and Code mode. For example:

156 - Ask: Find bugs in this codebase.

157 - Write code: Improve test coverage following the existing test patterns.

158 215

159## Track Codex usage216### What to verify

160 217

161- For workspaces with rate limits, use [Settings → Usage](https://chatgpt.com/codex/settings/usage) to view workspace metrics for Codex.218- Users can sign in to Codex local (ChatGPT or API key)

162- For more detail on enterprise governance, refer to the [Governance](https://developers.openai.com/codex/enterprise/governance) page.219- (If enabled) Users can sign in to Codex cloud (ChatGPT sign-in required)

163- For enterprise workspaces with flexible pricing, you can see credit usage in the ChatGPT workspace billing console.220- MFA and SSO requirements match your enterprise security policy

221- RBAC and workspace toggles produce the expected access behavior

222- Managed configuration is applied for users

223- Governance data is visible for admins

164 224

165## Zero data retention (ZDR)225For authentication options and enterprise login restrictions, see [Authentication](https://developers.openai.com/codex/auth).

166 226

167Codex supports OpenAI organizations with [Zero Data Retention (ZDR)](https://platform.openai.com/docs/guides/your-data#zero-data-retention) enabled.227Once your team is confident with setup, you can confidently roll Codex out to additional teams and organizations.

enterprise/governance.md +2 −0

Details

88 88

89The Compliance API gives enterprises a way to export logs and metadata for Codex activity so you can connect that data to your existing audit, monitoring, and security workflows. It is designed for use with tools like eDiscovery, DLP, SIEM, or other compliance systems.89The Compliance API gives enterprises a way to export logs and metadata for Codex activity so you can connect that data to your existing audit, monitoring, and security workflows. It is designed for use with tools like eDiscovery, DLP, SIEM, or other compliance systems.

90 90

91For Codex usage authenticated through ChatGPT, Compliance API exports provide audit records for Codex activity and can be used in investigations and compliance workflows. These audit logs are retained for up to 30 days. API-key-authenticated Codex usage follows your API organization settings and is not included in Compliance API exports.

91### What you can export93### What you can export

92 94

93#### Activity logs95#### Activity logs

enterprise/managed-configuration.md +192 −0 added

Details

1# Managed configuration

3Enterprise admins can control local Codex behavior in two ways:

5- **Requirements**: admin-enforced constraints that users can't override.

6- **Managed defaults**: starting values applied when Codex launches. Users can still change settings during a session; Codex reapplies managed defaults the next time it starts.

8## Admin-enforced requirements (requirements.toml)

10Requirements constrain security-sensitive settings (approval policy, sandbox mode, web search mode, and optionally which MCP servers can be enabled). When resolving configuration (for example from `config.toml`, profiles, or CLI config overrides), if a value conflicts with an enforced requirement, Codex falls back to a requirements-compatible value and notifies the user. If an `mcp_servers` allowlist is configured, Codex enables an MCP server only when both its name and identity match an approved entry; otherwise, Codex disables it.

12Requirements can also be used to constrain [feature flags](https://developers.openai.com/codex/config-basic/#feature-flags) via the `[features]` table in `requirements.toml`. Note features are generally not security-sensitive, but enterprises have the option of pinning values, if desired. Omitted keys remain unconstrained.

14For the exact key list, see the [`requirements.toml` section in Configuration Reference](https://developers.openai.com/codex/config-reference#requirementstoml).

16### Locations and precedence

18Requirements layers are applied in this order (earlier wins per field):

201. Cloud-managed requirements (ChatGPT Business or Enterprise)

212. macOS managed preferences (MDM) via `com.openai.codex:requirements_toml_base64`

223. System `requirements.toml` (`/etc/codex/requirements.toml` on Unix systems, including Linux/macOS)

24Across layers, requirements are merged per field: if an earlier layer sets a field (including an empty list), later layers do not override that field, but lower layers can still fill fields that remain unset.

26For backwards compatibility, Codex also interprets legacy `managed_config.toml` fields `approval_policy` and `sandbox_mode` as requirements (allowing only that single value).

28### Cloud-managed requirements

30When you sign in with ChatGPT on a Business or Enterprise plan, Codex can also fetch admin-enforced requirements from the Codex service. This is another source of `requirements.toml`-compatible requirements. This applies across Codex surfaces, including the CLI, App, and IDE Extension.

32#### Configure cloud-managed requirements

34Go to the [Codex managed-config page](https://chatgpt.com/codex/settings/managed-configs).

36Create a new managed requirements file using the same format and keys as `requirements.toml`.

38```toml

39enforce_residency = "us"

40allowed_approval_policies = ["on-request"]

41allowed_sandbox_modes = ["read-only", "workspace-write"]

43[rules]

44prefix_rules = [

45 { pattern = [{ any_of = ["bash", "sh", "zsh"] }], decision = "prompt", justification = "Require explicit approval for shell entrypoints" },

46]

47```

49Save the configuration. Once saved, the updated managed requirements apply immediately for matching users.

50For more examples, see [Example requirements.toml](#example-requirementstoml).

52#### Assign requirements to groups

54Admins can configure different managed requirements for different user groups, and also set a default fallback requirements policy.

56If a user matches multiple group-specific rules, the first matching rule applies. Codex does not fill unset requirement fields from later matching group rules.

58For example, if the first matching group rule sets only `allowed_sandbox_modes = ["read-only"]` and a later matching group rule sets `allowed_approval_policies = ["on-request"]`, Codex applies only the first matching group rule and does not fill `allowed_approval_policies` from the later rule.

60#### How Codex applies cloud-managed requirements locally

62When a user starts Codex and signs in with ChatGPT on a Business or Enterprise plan, Codex applies managed requirements on a best-effort basis. Codex first checks for a valid, unexpired local managed requirements cache entry and uses it if available. If the cache is missing, expired, invalid, or does not match the current auth identity, Codex attempts to fetch managed requirements from the service (with retries) and writes a new signed cache entry on success. If no valid cached entry is available and the fetch fails or times out, Codex continues without the managed requirements layer.

64After cache resolution, managed requirements are enforced as part of the normal requirements layering described above.

66### Example requirements.toml

68This example blocks `--ask-for-approval never` and `--sandbox danger-full-access` (including `--yolo`):

70```toml

71allowed_approval_policies = ["untrusted", "on-request"]

72allowed_sandbox_modes = ["read-only", "workspace-write"]

73```

75You can also constrain web search mode:

77```toml

78allowed_web_search_modes = ["cached"] # "disabled" remains implicitly allowed

79```

81`allowed_web_search_modes = []` effectively allows only `"disabled"`.

82For example, `allowed_web_search_modes = ["cached"]` prevents live web search even in `danger-full-access` sessions.

84You can also pin [feature flags](https://developers.openai.com/codex/config-basic/#feature-flags):

86```

87[features]

88personality = true

89unified_exec = false

90```

92Use the canonical feature keys from `config.toml`’s `[features]` table. Codex normalizes the effective feature set to satisfy these pins and rejects conflicting writes to `config.toml` or profile-scoped feature settings.

94### Enforce command rules from requirements

96Admins can also enforce restrictive command rules from `requirements.toml`

97using a `[rules]` table. These rules merge with regular `.rules` files, and the

98most restrictive decision still wins.

100Unlike `.rules`, requirements rules must specify `decision`, and that decision

101must be `"prompt"` or `"forbidden"` (not `"allow"`).

102

103```toml

104[rules]

105prefix_rules = [

106 { pattern = [{ token = "rm" }], decision = "forbidden", justification = "Use git clean -fd instead." },

107 { pattern = [{ token = "git" }, { any_of = ["push", "commit"] }], decision = "prompt", justification = "Require review before mutating history." },

108]

109```

110

111To restrict which MCP servers Codex can enable, add an `mcp_servers` approved list. For stdio servers, match on `command`; for streamable HTTP servers, match on `url`:

112

113```toml

114[mcp_servers.docs]

115identity = { command = "codex-mcp" }

116

117[mcp_servers.remote]

118identity = { url = "https://example.com/mcp" }

119```

120

121If `mcp_servers` is present but empty, Codex disables all MCP servers.

122

123## Managed defaults (`managed_config.toml`)

124

125Managed defaults merge on top of a user's local `config.toml` and take precedence over any CLI `--config` overrides, setting the starting values when Codex launches. Users can still change those settings during a session; Codex reapplies managed defaults the next time it starts.

126

127Make sure your managed defaults meet your requirements; Codex rejects disallowed values.

128

129### Precedence and layering

130

131Codex assembles the effective configuration in this order (top overrides bottom):

132

133- Managed preferences (macOS MDM; highest precedence)

134- `managed_config.toml` (system/managed file)

135- `config.toml` (user's base configuration)

136

137CLI `--config key=value` overrides apply to the base, but managed layers override them. This means each run starts from the managed defaults even if you provide local flags.

138

139Cloud-managed requirements affect the requirements layer (not managed defaults). See the Admin-enforced requirements section above for precedence.

140

141### Locations

142

143- Linux/macOS (Unix): `/etc/codex/managed_config.toml`

144- Windows/non-Unix: `~/.codex/managed_config.toml`

145

146If the file is missing, Codex skips the managed layer.

147

148### macOS managed preferences (MDM)

149

150On macOS, admins can push a device profile that provides base64-encoded TOML payloads at:

151

152- Preference domain: `com.openai.codex`

153- Keys:

154 - `config_toml_base64` (managed defaults)

155 - `requirements_toml_base64` (requirements)

156

157Codex parses these "managed preferences" payloads as TOML. For managed defaults (`config_toml_base64`), managed preferences have the highest precedence. For requirements (`requirements_toml_base64`), precedence follows the cloud-managed requirements order described above. The same requirements-side `[features]` table works in `requirements_toml_base64`; use canonical feature keys there as well.

158

159### MDM setup workflow

160

161Codex honors standard macOS MDM payloads, so you can distribute settings with tooling like `Jamf Pro`, `Fleet`, or `Kandji`. A lightweight deployment looks like:

162

1631. Build the managed payload TOML and encode it with `base64` (no wrapping).

1642. Drop the string into your MDM profile under the `com.openai.codex` domain at `config_toml_base64` (managed defaults) or `requirements_toml_base64` (requirements).

1653. Push the profile, then ask users to restart Codex and confirm the startup config summary reflects the managed values.

1664. When revoking or changing policy, update the managed payload; the CLI reads the refreshed preference the next time it launches.

167

168Avoid embedding secrets or high-churn dynamic values in the payload. Treat the managed TOML like any other MDM setting under change control.

169

170### Example managed_config.toml

171

172```toml

173# Set conservative defaults

174approval_policy = "on-request"

175sandbox_mode = "workspace-write"

176

177[sandbox_workspace_write]

178network_access = false # keep network disabled unless explicitly allowed

179

180[otel]

181environment = "prod"

182exporter = "otlp-http" # point at your collector

183log_user_prompt = false # keep prompts redacted

184# exporter details live under exporter tables; see Monitoring and telemetry above

185```

186

187### Recommended guardrails

188

189- Prefer `workspace-write` with approvals for most users; reserve full access for controlled containers.

190- Keep `network_access = false` unless your security review allows a collector or domains required by your workflows.

191- Use managed configuration to pin OTel settings (exporter, environment), but keep `log_user_prompt = false` unless your policy explicitly allows storing prompt contents.

192- Periodically audit diffs between local `config.toml` and managed policy to catch drift; managed layers should win over local flags and files.

ide/features.md +1 −1

Details

57 57

58## Web search58## Web search

59 59

60Codex ships with a first-party web search tool. For local tasks in the Codex IDE Extension, Codex enables web search by default and serves results from a web search cache. The cache is an OpenAI-maintained index of web results, so cached mode returns pre-indexed results instead of fetching live pages. This reduces exposure to prompt injection from arbitrary live content, but you should still treat web results as untrusted. If you configure your sandbox for [full access](https://developers.openai.com/codex/security), web search defaults to live results. See [Config basics](https://developers.openai.com/codex/config-basic) to disable web search or switch to live results that fetch the most recent data.60Codex ships with a first-party web search tool. For local tasks in the Codex IDE Extension, Codex enables web search by default and serves results from a web search cache. The cache is an OpenAI-maintained index of web results, so cached mode returns pre-indexed results instead of fetching live pages. This reduces exposure to prompt injection from arbitrary live content, but you should still treat web results as untrusted. If you configure your sandbox for [full access](https://developers.openai.com/codex/agent-approvals-security), web search defaults to live results. See [Config basics](https://developers.openai.com/codex/config-basic) to disable web search or switch to live results that fetch the most recent data.

61 61

62You'll see `web_search` items in the transcript or `codex exec --json` output whenever Codex looks something up.62You'll see `web_search` items in the transcript or `codex exec --json` output whenever Codex looks something up.

63 63

integrations/linear.md +1 −1

Details

62 62

63When you mention `@Codex` or assign an issue to it, Codex receives your issue content to understand your request and create a task.63When you mention `@Codex` or assign an issue to it, Codex receives your issue content to understand your request and create a task.

64Data handling follows OpenAI's [Privacy Policy](https://openai.com/privacy), [Terms of Use](https://openai.com/terms/), and other applicable [policies](https://openai.com/policies).64Data handling follows OpenAI's [Privacy Policy](https://openai.com/privacy), [Terms of Use](https://openai.com/terms/), and other applicable [policies](https://openai.com/policies).

~~65For more on security, see the [Codex security documentation](https://developers.openai.com/codex/security).~~65For more on security, see the [Codex security documentation](https://developers.openai.com/codex/agent-approvals-security).

66 66

67Codex uses large language models that can make mistakes. Always review answers and diffs.67Codex uses large language models that can make mistakes. Always review answers and diffs.

68 68

integrations/slack.md +1 −1

Details

31 31

32When you mention `@Codex`, Codex receives your message and thread history to understand your request and create a task.32When you mention `@Codex`, Codex receives your message and thread history to understand your request and create a task.

33Data handling follows OpenAI's [Privacy Policy](https://openai.com/privacy), [Terms of Use](https://openai.com/terms/), and other applicable [policies](https://openai.com/policies).33Data handling follows OpenAI's [Privacy Policy](https://openai.com/privacy), [Terms of Use](https://openai.com/terms/), and other applicable [policies](https://openai.com/policies).

~~34For more on security, see the Codex [security documentation](https://developers.openai.com/codex/security).~~34For more on security, see the Codex [security documentation](https://developers.openai.com/codex/agent-approvals-security).

35 35

36Codex uses large language models that can make mistakes. Always review answers and diffs.36Codex uses large language models that can make mistakes. Always review answers and diffs.

37 37

mcp.md +9 −1

Details

75- `enabled_tools` (optional): Tool allow list.75- `enabled_tools` (optional): Tool allow list.

76- `disabled_tools` (optional): Tool deny list (applied after `enabled_tools`).76- `disabled_tools` (optional): Tool deny list (applied after `enabled_tools`).

77 77

~~78If your OAuth provider requires a static callback URI, set the top-level `mcp_oauth_callback_port` in `config.toml`. If unset, Codex binds to an ephemeral port.~~78If your OAuth provider requires a fixed callback port, set the top-level `mcp_oauth_callback_port` in `config.toml`. If unset, Codex binds to an ephemeral port.

80If your MCP OAuth flow must use a specific callback URL (for example, a remote devbox ingress URL or a custom callback path), set `mcp_oauth_callback_url`. Codex uses this value as the OAuth `redirect_uri` while still using `mcp_oauth_callback_port` for the callback listener port. Local callback URLs (for example `localhost`) bind on loopback; non-local callback URLs bind on `0.0.0.0` so the callback can reach the host.

79 81

80#### config.toml examples82#### config.toml examples

81 83

88MY_ENV_VAR = "MY_ENV_VALUE"90MY_ENV_VAR = "MY_ENV_VALUE"

89```91```

90 92

93```toml

94# Optional MCP OAuth callback overrides (used by `codex mcp login`)

95mcp_oauth_callback_port = 5555

96mcp_oauth_callback_url = "https://devbox.example.internal/callback"

97```

91```toml99```toml

92[mcp_servers.figma]100[mcp_servers.figma]

93url = "https://mcp.figma.com/mcp"101url = "https://mcp.figma.com/mcp"

models.md +32 −20

Details

2 2

3## Recommended models3## Recommended models

4 4

~~5![gpt-5.3-codex](/images/codex/codex-wallpaper-1.webp)~~5![gpt-5.4](/images/api/models/gpt-5.4.jpg)

6 6

~~7gpt-5.3-codex~~7gpt-5.4

8 8

~~9Most capable agentic coding model to date, combining frontier coding performance with stronger reasoning and professional knowledge capabilities.~~9Flagship frontier model for professional work that brings the industry-leading coding capabilities of GPT-5.3-Codex together with stronger reasoning, tool use, and agentic workflows.

10 10

~~11codex -m gpt-5.3-codex~~11codex -m gpt-5.4

12 12

13Copy command13Copy command

14 14

26 26

27API Access27API Access

28 28

~~29![gpt-5.3-codex-spark](/images/codex/codex-wallpaper-2.webp)~~29![gpt-5.3-codex](/images/codex/codex-wallpaper-1.webp)

30 30

~~31gpt-5.3-codex-spark~~31gpt-5.3-codex

32 32

~~33Text-only research preview model optimized for near-instant, real-time coding iteration. Available to ChatGPT Pro users.~~33Industry-leading coding model for complex software engineering. Its coding capabilities now also power GPT-5.4.

34 34

~~35codex -m gpt-5.3-codex-spark~~35codex -m gpt-5.3-codex

36 36

37Copy command37Copy command

38 38

50 50

51API Access51API Access

52 52

~~53![gpt-5.2-codex](/images/codex/gpt-5.2-codex.png)~~53![gpt-5.3-codex-spark](/images/codex/codex-wallpaper-2.webp)

54 54

~~55gpt-5.2-codex~~55gpt-5.3-codex-spark

56 56

~~57Advanced coding model for real-world engineering. Succeeded by GPT-5.3-Codex.~~57Text-only research preview model optimized for near-instant, real-time coding iteration. Available to ChatGPT Pro users.

58 58

~~59codex -m gpt-5.2-codex~~59codex -m gpt-5.3-codex-spark

60 60

61Copy command61Copy command

62 62

74 74

75API Access75API Access

76 76

~~77For most coding tasks in Codex, start with gpt-5.3-codex. It is available for~~77For most tasks in Codex, start with `gpt-5.4`. It combines strong coding,

~~78ChatGPT-authenticated Codex sessions in the Codex app, CLI, IDE extension, and~~78reasoning, native computer use, and broader professional workflows in one

~~79Codex Cloud. API access for GPT-5.3-Codex will come soon. The~~79model. The `gpt-5.3-codex-spark` model is available in research preview for

~~80gpt-5.3-codex-spark model is available in research preview for ChatGPT Pro~~80ChatGPT Pro subscribers and is optimized for near-instant, real-time coding

~~81subscribers.~~81iteration.

82 82

83## Alternative models83## Alternative models

84 84

85![gpt-5.2-codex](/images/codex/gpt-5.2-codex.png)

87gpt-5.2-codex

89Advanced coding model for real-world engineering. Succeeded by GPT-5.3-Codex.

91codex -m gpt-5.2-codex

93Copy command

95Show details

85![gpt-5.2](/images/api/models/gpt-5.2.jpg)97![gpt-5.2](/images/api/models/gpt-5.2.jpg)

86 98

87gpt-5.299gpt-5.2

88 100

~~89Our best general agentic model for tasks across industries and domains.~~101Previous general-purpose model for coding and agentic tasks across industries and domains. Succeeded by GPT-5.4.

90 102

91codex -m gpt-5.2103codex -m gpt-5.2

92 104

182The Codex CLI and IDE extension use the same `config.toml` [configuration file](https://developers.openai.com/codex/config-basic). To specify a model, add a `model` entry to your configuration file. If you don't specify a model, the Codex app, CLI, or IDE Extension defaults to a recommended model.194The Codex CLI and IDE extension use the same `config.toml` [configuration file](https://developers.openai.com/codex/config-basic). To specify a model, add a `model` entry to your configuration file. If you don't specify a model, the Codex app, CLI, or IDE Extension defaults to a recommended model.

183 195

184```196```

185model = "gpt-5.2"197model = "gpt-5.4"

186```198```

187 199

188### Choosing a different local model temporarily200### Choosing a different local model temporarily

192To start a new Codex CLI thread with a specific model or to specify the model for `codex exec` you can use the `--model`/`-m` flag:204To start a new Codex CLI thread with a specific model or to specify the model for `codex exec` you can use the `--model`/`-m` flag:

193 205

194```bash206```bash

195codex -m gpt-5.3-codex207codex -m gpt-5.4

196```208```

197 209

198### Choosing your model for cloud tasks210### Choosing your model for cloud tasks

multi-agent.md +200 −18

Details

4 4

5With multi-agent workflows you can also define your own set of agents with different model configurations and instructions depending on the agent.5With multi-agent workflows you can also define your own set of agents with different model configurations and instructions depending on the agent.

6 6

7For the concepts and tradeoffs behind multi-agent workflows (including context pollution/context rot and model-selection guidance), see [Multi-agents concepts](https://developers.openai.com/codex/concepts/multi-agents).

7## Enable multi-agent9## Enable multi-agent

8 10

9Multi-agent workflows are currently experimental and need to be explicitly enabled.11Multi-agent workflows are currently experimental and need to be explicitly enabled.

29 31

30Codex will automatically decide when to spawn a new agent or you can explicitly ask it to do so.32Codex will automatically decide when to spawn a new agent or you can explicitly ask it to do so.

31 33

34For long-running commands or polling workflows, Codex can also use the built-in `monitor` role, which is tuned for waiting and repeated status checks.

32To see it in action, try the following prompt on your project:36To see it in action, try the following prompt on your project:

33 37

34```38```

45 49

46- Use `/agent` in the CLI to switch between active agent threads and inspect the ongoing thread.50- Use `/agent` in the CLI to switch between active agent threads and inspect the ongoing thread.

47- Ask Codex directly to steer a running sub-agent, stop it, or close completed agent threads.51- Ask Codex directly to steer a running sub-agent, stop it, or close completed agent threads.

52- The `wait` tool supports long polling windows for monitoring workflows (up to 1 hour per call).

54## Process CSV batches with sub-agents

56Use `spawn_agents_on_csv` when you have many similar tasks that can be expressed as one row per work item. Codex reads the CSV, spawns one worker sub-agent per row, waits for the full batch to finish, and exports the combined results to CSV.

58This works well for repeated audits such as:

60- reviewing one file, package, or service per row

61- checking a list of incidents, PRs, or migration targets

62- generating structured summaries for many similar inputs

64The tool accepts:

66- `csv_path` for the source CSV

67- `instruction` for the worker prompt template, using `{column_name}` placeholders

68- `id_column` when you want stable item ids from a specific column

69- `output_schema` when each worker should return a JSON object with a fixed shape

70- `output_csv_path`, `max_concurrency`, and `max_runtime_seconds` for job control

72Each worker must call `report_agent_job_result` exactly once. If a worker exits without reporting a result, that row is marked as failed in the exported CSV.

74Example prompt:

76```

77Create /tmp/components.csv with columns path,owner and one row per frontend component.

79Then call spawn_agents_on_csv with:

80- csv_path: /tmp/components.csv

81- id_column: path

82- instruction: "Review {path} owned by {owner}. Return JSON with keys path, risk, summary, and follow_up via report_agent_job_result."

83- output_csv_path: /tmp/components-review.csv

84- output_schema: an object with required string fields path, risk, summary, and follow_up

85```

87When you run this through `codex exec`, Codex shows a single-line progress update on `stderr` while the batch is running. The exported CSV includes the original row data plus metadata such as `job_id`, `item_id`, `status`, `last_error`, and `result_json`.

89Related runtime settings:

91- `agents.max_threads` caps how many agent threads can stay open concurrently.

92- `agents.job_max_runtime_seconds` sets the default per-worker timeout for CSV fan-out jobs. A per-call `max_runtime_seconds` override takes precedence.

93- `sqlite_home` controls where Codex stores the SQLite-backed state used for agent jobs and their exported results.

48 94

49## Approvals and sandbox controls95## Approvals and sandbox controls

50 96

~~51Sub-agents inherit your current sandbox policy, but they run with~~97Sub-agents inherit your current sandbox policy.

~~52non-interactive approvals. If a sub-agent attempts an action that would require~~98

~~53a new approval, that action fails and the error is surfaced in the parent~~99In interactive CLI sessions, approval requests can surface from inactive agent

~~54workflow.~~100threads even while you are looking at the main thread. The approval overlay

101shows the source thread label, and you can press `o` to open that thread before

102you approve, reject, or answer the request.

103

104In non-interactive flows, or whenever a run cannot surface a fresh approval,

105an action that needs new approval fails and the error is surfaced back to the

106parent workflow.

107

108Codex also reapplies the parent turn’s live runtime overrides when it spawns a

109child. That includes sandbox and approval choices you set interactively during

110the session, such as `/approvals` changes or `--yolo`, even if the selected

111agent role loads a config file with different defaults.

55 112

56You can also override the sandbox configuration for individual [agent roles](#agent-roles) such as explicitly marking an agent to work in read-only mode.113You can also override the sandbox configuration for individual [agent roles](#agent-roles) such as explicitly marking an agent to work in read-only mode.

57 114

66 123

67Codex ships with built-in roles:124Codex ships with built-in roles:

68 125

~~69- `default`~~126- `default`: general-purpose fallback role.

~~70- `worker`~~127- `worker`: execution-focused role for implementation and fixes.

~~71- `explorer`~~128- `explorer`: read-heavy codebase exploration role.

129- `monitor`: long-running command/task monitoring role (optimized for waiting/polling).

72 130

73Each agent role can override your default configuration. Common settings to override for an agent role are:131Each agent role can override your default configuration. Common settings to override for an agent role are:

74 132

82| --- | --- | --- | --- |140| --- | --- | --- | --- |

88**Notes:**148**Notes:**

89 149

90- Unknown fields in `[agents.<name>]` are rejected.150- Unknown fields in `[agents.<name>]` are rejected.

151- `agents.max_depth` defaults to `1`, which allows a direct child agent to spawn but prevents deeper nesting.

152- `agents.job_max_runtime_seconds` is optional. When you leave it unset, `spawn_agents_on_csv` falls back to its per-call default timeout of 1800 seconds per worker.

91- Relative `config_file` paths are resolved relative to the `config.toml` file that defines the role.153- Relative `config_file` paths are resolved relative to the `config.toml` file that defines the role.

154- `agents.<name>.config_file` is validated at config load time and must point to an existing file.

92- If a role name matches a built-in role (for example, `explorer`), your user-defined role takes precedence.155- If a role name matches a built-in role (for example, `explorer`), your user-defined role takes precedence.

93- If Codex can’t load a role config file, agent spawns can fail until you fix the file.156- If Codex can’t load a role config file, agent spawns can fail until you fix the file.

94- Any configuration not set by the agent role will be inherited from the parent session.157- Any configuration not set by the agent role will be inherited from the parent session.

95 158

96### Example agent roles159### Example agent roles

97 160

~~98Below is an example that overrides the definitions for the built-in `default` and `explorer` agent roles and defines a new `reviewer` role.~~161The best role definitions are narrow and opinionated. Give each role one clear job, a tool surface that matches that job, and instructions that keep it from drifting into adjacent work.

162

163#### Example 1: PR review team

164

165This pattern splits review into three focused roles:

99 166

100Example `~/.codex/config.toml`:167- `explorer` maps the codebase and gathers evidence.

168- `reviewer` looks for correctness, security, and test risks.

169- `docs_researcher` checks framework or API documentation through a dedicated MCP server.

170

171Project config (`.codex/config.toml`):

101 172

102```173```

103[agents.default]174[agents]

104description = "General-purpose helper."175max_threads = 6

176max_depth = 1

177

178[agents.explorer]

179description = "Read-only codebase explorer for gathering evidence before changes are proposed."

180config_file = "agents/explorer.toml"

105 181

106[agents.reviewer]182[agents.reviewer]

107description = "Find security, correctness, and test risks in code."183description = "PR reviewer focused on correctness, security, and missing tests."

108config_file = "agents/reviewer.toml"184config_file = "agents/reviewer.toml"

109 185

110[agents.explorer]186[agents.docs_researcher]

111description = "Fast codebase explorer for read-heavy tasks."187description = "Documentation specialist that uses the docs MCP server to verify APIs and framework behavior."

112config_file = "agents/custom-explorer.toml"188config_file = "agents/docs-researcher.toml"

113```189```

114 190

115Example config file for the `reviewer` role (`~/.codex/agents/reviewer.toml`):191`agents/explorer.toml`:

192

193```

194model = "gpt-5.3-codex-spark"

195model_reasoning_effort = "medium"

196sandbox_mode = "read-only"

197developer_instructions = """

198Stay in exploration mode.

199Trace the real execution path, cite files and symbols, and avoid proposing fixes unless the parent agent asks for them.

200Prefer fast search and targeted file reads over broad scans.

201"""

202```

203

204`agents/reviewer.toml`:

116 205

117```206```

118model = "gpt-5.3-codex"207model = "gpt-5.3-codex"

119model_reasoning_effort = "high"208model_reasoning_effort = "high"

120developer_instructions = "Focus on high priority issues, write tests to validate hypothesis before flagging an issue. When finding security issues give concrete steps on how to reproduce the vulnerability."209sandbox_mode = "read-only"

210developer_instructions = """

211Review code like an owner.

212Prioritize correctness, security, behavior regressions, and missing test coverage.

213Lead with concrete findings, include reproduction steps when possible, and avoid style-only comments unless they hide a real bug.

214"""

215```

216

217`agents/docs-researcher.toml`:

218

219```

220model = "gpt-5.3-codex-spark"

221model_reasoning_effort = "medium"

222sandbox_mode = "read-only"

223developer_instructions = """

224Use the docs MCP server to confirm APIs, options, and version-specific behavior.

225Return concise answers with links or exact references when available.

226Do not make code changes.

227"""

228

229[mcp_servers.openaiDeveloperDocs]

230url = "https://developers.openai.com/mcp"

231```

232

233This setup works well for prompts like:

234

235```

236Review this branch against main. Have explorer map the affected code paths, reviewer find real risks, and docs_researcher verify the framework APIs that the patch relies on.

121```237```

122 238

123Example config file for the `explorer` role (`~/.codex/agents/custom-explorer.toml`):239#### Example 2: frontend integration debugging team

240

241This pattern is useful for UI regressions, flaky browser flows, or integration bugs that cross application code and the running product.

242

243Project config (`.codex/config.toml`):

244

245```

246[agents]

247max_threads = 6

248max_depth = 1

249

250[agents.explorer]

251description = "Read-only codebase explorer for locating the relevant frontend and backend code paths."

252config_file = "agents/explorer.toml"

253

254[agents.browser_debugger]

255description = "UI debugger that uses browser tooling to reproduce issues and capture evidence."

256config_file = "agents/browser-debugger.toml"

257

258[agents.worker]

259description = "Implementation-focused agent for small, targeted fixes after the issue is understood."

260config_file = "agents/worker.toml"

261```

262

263`agents/explorer.toml`:

124 264

125```265```

126model = "gpt-5.3-codex-spark"266model = "gpt-5.3-codex-spark"

127model_reasoning_effort = "medium"267model_reasoning_effort = "medium"

128sandbox_mode = "read-only"268sandbox_mode = "read-only"

269developer_instructions = """

270Map the code that owns the failing UI flow.

271Identify entry points, state transitions, and likely files before the worker starts editing.

272"""

273```

274

275`agents/browser-debugger.toml`:

276

277```

278model = "gpt-5.3-codex"

279model_reasoning_effort = "high"

280sandbox_mode = "workspace-write"

281developer_instructions = """

282Reproduce the issue in the browser, capture exact steps, and report what the UI actually does.

283Use browser tooling for screenshots, console output, and network evidence.

284Do not edit application code.

285"""

286

287[mcp_servers.chrome_devtools]

288url = "http://localhost:3000/mcp"

289startup_timeout_sec = 20

290```

291

292`agents/worker.toml`:

293

294```

295model = "gpt-5.3-codex"

296model_reasoning_effort = "medium"

297developer_instructions = """

298Own the fix once the issue is reproduced.

299Make the smallest defensible change, keep unrelated files untouched, and validate only the behavior you changed.

300"""

301

302[[skills.config]]

303path = "/Users/me/.agents/skills/docs-editor/SKILL.md"

304enabled = false

305```

306

307This setup works well for prompts like:

308

309```

310Investigate why the settings modal fails to save. Have browser_debugger reproduce it, explorer trace the responsible code path, and worker implement the smallest fix once the failure mode is clear.

129```311```

noninteractive.md +22 −0

Details

111 111

112`codex exec` reuses saved CLI authentication by default. In CI, it's common to provide credentials explicitly:112`codex exec` reuses saved CLI authentication by default. In CI, it's common to provide credentials explicitly:

113 113

114### Use API key auth (recommended)

115

114- Set `CODEX_API_KEY` as a secret environment variable for the job.116- Set `CODEX_API_KEY` as a secret environment variable for the job.

115- Keep prompts and tool output in mind: they can include sensitive code or data.117- Keep prompts and tool output in mind: they can include sensitive code or data.

116 118

122 124

123`CODEX_API_KEY` is only supported in `codex exec`.125`CODEX_API_KEY` is only supported in `codex exec`.

124 126

127Use ChatGPT-managed auth in CI/CD (advanced)

128

129Read this if you need to run CI/CD jobs with a Codex user account instead of an

130API key, such as enterprise teams using ChatGPT-managed Codex access on trusted

131runners or users who need ChatGPT/Codex rate limits instead of API key usage.

132

133API keys are the right default for automation because they are simpler to

134provision and rotate. Use this path only if you specifically need to run as

135your Codex account.

136

137Treat `~/.codex/auth.json` like a password: it contains access tokens. Don't

138commit it, paste it into tickets, or share it in chat.

139

140Do not use this workflow for public or open-source repositories. If `codex login`

141is not an option on the runner, seed `auth.json` through secure storage, run

142Codex on the runner so Codex refreshes it in place, and persist the updated file

143between runs.

144

145See [Maintain Codex account auth in CI/CD (advanced)](https://developers.openai.com/codex/auth/ci-cd-auth).

146

125## Resume a non-interactive session147## Resume a non-interactive session

126 148

127If you need to continue a previous run (for example, a two-stage pipeline), use the `resume` subcommand:149If you need to continue a previous run (for example, a two-stage pipeline), use the `resume` subcommand:

open-source.md +2 −0

Details

2 2

3OpenAI develops key parts of Codex in the open. That work lives on GitHub so you can follow progress, report issues, and contribute improvements.3OpenAI develops key parts of Codex in the open. That work lives on GitHub so you can follow progress, report issues, and contribute improvements.

4 4

5If you maintain a widely used open-source project or want to nominate maintainers stewarding important projects, you can also [apply to the Codex open source program](https://developers.openai.com/codex/community/codex-for-oss) for API credits, ChatGPT Pro with Codex, and selective access to Codex Security.

5## Open-source components7## Open-source components

6 8

overview.md +6 −2

Details

22 22

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

24 24

~~25Join the OpenAI Discord to ask questions, share workflows and connect with others.~~25Explore Codex Ambassadors and upcoming community meetups by location.

26 26

~~27 Join the Discord](https://discord.gg/openai)~~27 See community](https://developers.openai.com/codex/community/meetups) [### Codex for OSS

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

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

prompting.md +1 −1

Details

31 31

32Threads can run either locally or in the cloud:32Threads can run either locally or in the cloud:

33 33

34- **Local threads** run on your machine. Codex can read and edit your files and run commands, so you can see what changes and use your existing tools. To reduce the risk of unwanted changes outside your workspace, local threads run in a [sandbox](https://developers.openai.com/codex/security).34- **Local threads** run on your machine. Codex can read and edit your files and run commands, so you can see what changes and use your existing tools. To reduce the risk of unwanted changes outside your workspace, local threads run in a [sandbox](https://developers.openai.com/codex/agent-approvals-security).

35- **Cloud threads** run in an isolated [environment](https://developers.openai.com/codex/cloud/environments). Codex clones your repository and checks out the branch it's working on. Cloud threads are useful when you want to run work in parallel or delegate tasks from another device. To use cloud threads with your repo, push your code to GitHub first. You can also [delegate tasks from your local machine](https://developers.openai.com/codex/ide/cloud-tasks), which includes your current working state.35- **Cloud threads** run in an isolated [environment](https://developers.openai.com/codex/cloud/environments). Codex clones your repository and checks out the branch it's working on. Cloud threads are useful when you want to run work in parallel or delegate tasks from another device. To use cloud threads with your repo, push your code to GitHub first. You can also [delegate tasks from your local machine](https://developers.openai.com/codex/ide/cloud-tasks), which includes your current working state.

36 36

37## Context37## Context

quickstart.md +2 −2

Details

14 14

151. Download and install the Codex app151. Download and install the Codex app

16 16

~~17 The Codex app is currently only available for macOS.~~17 Download the Codex app for Windows or macOS.

18 18

19 [Download for macOS](https://persistent.oaistatic.com/codex-app-prod/Codex.dmg)19 [Download for macOS](https://persistent.oaistatic.com/codex-app-prod/Codex.dmg)

20 20

~~21 [Get notified for Windows and Linux](https://openai.com/form/codex-app/)~~21 [Get notified for Linux](https://openai.com/form/codex-app/)

222. Open Codex and sign in222. Open Codex and sign in

23 23

24 Once you downloaded and installed the Codex app, open it and sign in with your ChatGPT account or an OpenAI API key.24 Once you downloaded and installed the Codex app, open it and sign in with your ChatGPT account or an OpenAI API key.

rules.md +1 −1

Details

43carefully before accepting it.43carefully before accepting it.

44 44

45Admins can also enforce restrictive `prefix_rule` entries from45Admins can also enforce restrictive `prefix_rule` entries from

~~46[`requirements.toml`](https://developers.openai.com/codex/security#admin-enforced-requirements-requirementstoml).~~46[`requirements.toml`](https://developers.openai.com/codex/enterprise/managed-configuration#admin-enforced-requirements-requirementstoml).

47 47

48## Understand rule fields48## Understand rule fields

49 49

security.md +22 −370

Details

1# Codex Security1# Codex Security

2 2

~~3Codex helps protect your code and data and reduces the risk of misuse.~~3Codex Security helps engineering and security teams find, validate, and remediate likely vulnerabilities in connected GitHub repositories.

4 4

5By default, the agent runs with network access turned off. Locally, Codex uses an OS-enforced sandbox that limits what it can touch (typically to the current workspace), plus an approval policy that controls when it must stop and ask you before acting.5This page covers Codex Security, the product that scans connected GitHub

6 repositories for likely security issues. For Codex sandboxing, approvals,

7 network controls, and admin settings, see [Agent approvals &

8 security](https://developers.openai.com/codex/agent-approvals-security).

6 9

~~7## Sandbox and approvals~~10It helps teams:

8 11

~~9Codex security controls come from two layers that work together:~~121. **Find likely vulnerabilities** by using a repo-specific threat model and real code context.

132. **Reduce noise** by validating findings before you review them.

143. **Move findings toward fixes** with ranked results, evidence, and suggested patch options.

10 15

~~11- **Sandbox mode**: What Codex can do technically (for example, where it can write and whether it can reach the network) when it executes model-generated commands.~~16## How it works

~~12- **Approval policy**: When Codex must ask you before it executes an action (for example, leaving the sandbox, using the network, or running commands outside a trusted set).~~

13 17

~~14Codex uses different sandbox modes depending on where you run it:~~18Codex Security scans connected repositories commit by commit.

19It builds scan context from your repo, checks likely vulnerabilities against that context, and validates high-signal issues in an isolated environment before surfacing them.

15 20

16- **Codex cloud**: Runs in isolated OpenAI-managed containers, preventing access to your host system or unrelated data. You can expand access intentionally (for example, to install dependencies or allow specific domains) when needed. Network access is always enabled during the setup phase, which runs before the agent has access to your code.21You get a workflow focused on:

17- **Codex CLI / IDE extension**: OS-level mechanisms enforce sandbox policies. Defaults include no network access and write permissions limited to the active workspace. You can configure the sandbox, approval policy, and network settings based on your risk tolerance.

18 22

~~19In the `Auto` preset (for example, `--full-auto`), Codex can read files, make edits, and run commands in the working directory automatically.~~23- repo-specific context instead of generic signatures

24- validation evidence that helps reduce false positives

25- suggested fixes you can review in GitHub

20 26

21Codex asks for approval to edit files outside the workspace or to run commands that require network access. If you want to chat or plan without making changes, switch to `read-only` mode with the `/permissions` command.27## Access and prerequisites

22 28

~~23Codex can also elicit approval for app (connector) tool calls that advertise side effects, even when the action isn’t a shell command or file change.~~29Codex Security works with connected GitHub repositories through Codex cloud. OpenAI manages access. If you need access or a repository isn’t visible, contact your OpenAI account team and confirm the repository is available through your Codex cloud workspace.

24 30

~~25## Network access [Elevated Risk](https://help.openai.com/articles/20001061)~~31## Related docs

26 32

~~27For Codex cloud, see [agent internet access](https://developers.openai.com/codex/cloud/internet-access) to enable full internet access or a domain allow list.~~33- [Codex Security setup](https://developers.openai.com/codex/security/setup) covers setup, scanning, and findings review.

28 34- [FAQ](https://developers.openai.com/codex/security/faq) covers common product questions.

~~29For the Codex app, CLI, or IDE Extension, the default `workspace-write` sandbox mode keeps network access turned off unless you enable it in your configuration:~~35- [Improving the threat model](https://developers.openai.com/codex/security/threat-model) explains how to tune scope, attack surface, and criticality assumptions.

~~31```~~

~~32[sandbox_workspace_write]~~

~~33network_access = true~~

~~34```~~

36You can also control the [web search tool](https://platform.openai.com/docs/guides/tools-web-search) without granting full network access to spawned commands. Codex defaults to using a web search cache to access results. The cache is an OpenAI-maintained index of web results, so cached mode returns pre-indexed results instead of fetching live pages. This reduces exposure to prompt injection from arbitrary live content, but you should still treat web results as untrusted. If you are using `--yolo` or another [full access sandbox setting](#common-sandbox-and-approval-combinations), web search defaults to live results. Use `--search` or set `web_search = "live"` to allow live browsing, or set it to `"disabled"` to turn the tool off:

~~38```~~

~~39web_search = "cached" # default~~

~~40# web_search = "disabled"~~

~~41# web_search = "live" # same as --search~~

~~42```~~

~~44Use caution when enabling network access or web search in Codex. Prompt injection can cause the agent to fetch and follow untrusted instructions.~~

~~46## Defaults and recommendations~~

~~48- On launch, Codex detects whether the folder is version-controlled and recommends:~~

~~49 - Version-controlled folders: `Auto` (workspace write + on-request approvals)~~

~~50 - Non-version-controlled folders: `read-only`~~

~~51- Depending on your setup, Codex may also start in `read-only` until you explicitly trust the working directory (for example, via an onboarding prompt or `/permissions`).~~

~~52- The workspace includes the current directory and temporary directories like `/tmp`. Use the `/status` command to see which directories are in the workspace.~~

~~53- To accept the defaults, run `codex`.~~

~~54- You can set these explicitly:~~

~~55 - `codex --sandbox workspace-write --ask-for-approval on-request`~~

~~56 - `codex --sandbox read-only --ask-for-approval on-request`~~

~~58### Protected paths in writable roots~~

~~60In the default `workspace-write` sandbox policy, writable roots still include protected paths:~~

~~62- `<writable_root>/.git` is protected as read-only whether it appears as a directory or file.~~

~~63- If `<writable_root>/.git` is a pointer file (`gitdir: ...`), the resolved Git directory path is also protected as read-only.~~

~~64- `<writable_root>/.agents` is protected as read-only when it exists as a directory.~~

~~65- `<writable_root>/.codex` is protected as read-only when it exists as a directory.~~

~~66- Protection is recursive, so everything under those paths is read-only.~~

~~68### Run without approval prompts~~

~~70You can disable approval prompts with `--ask-for-approval never` or `-a never` (shorthand).~~

~~72This option works with all `--sandbox` modes, so you still control Codex’s level of autonomy. Codex makes a best effort within the constraints you set.~~

74If 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.

~~76### Common sandbox and approval combinations~~

~~78| Intent | Flags | Effect |~~

~~79| --- | --- | --- |~~

80| Auto (preset) | *no flags needed* or `--full-auto` | Codex can read files, make edits, and run commands in the workspace. Codex requires approval to edit outside the workspace or to access network. |

~~81| Safe read-only browsing | `--sandbox read-only --ask-for-approval on-request` | Codex can read files and answer questions. Codex requires approval to make edits, run commands, or access network. |~~

~~82| Read-only non-interactive (CI) | `--sandbox read-only --ask-for-approval never` | Codex can only read files; never asks for approval. |~~

83| Automatically edit but ask for approval to run untrusted commands | `--sandbox workspace-write --ask-for-approval untrusted` | Codex can read and edit files but asks for approval before running untrusted commands. |

~~84| Dangerous full access | `--dangerously-bypass-approvals-and-sandbox` (alias: `--yolo`) | [Elevated Risk](https://help.openai.com/articles/20001061) No sandbox; no approvals *(not recommended)* |~~

~~86`--full-auto` is a convenience alias for `--sandbox workspace-write --ask-for-approval on-request`.~~

88With `--ask-for-approval untrusted`, Codex runs only known-safe read operations automatically. Commands that can mutate state or trigger external execution paths (for example, destructive Git operations or Git output/config-override flags) require approval.

~~90#### Configuration in `config.toml`~~

~~92```~~

~~93# Always ask for approval mode~~

~~94approval_policy = "untrusted"~~

~~95sandbox_mode = "read-only"~~

~~97# Optional: Allow network in workspace-write mode~~

~~98[sandbox_workspace_write]~~

~~99network_access = true~~

100```

~~101~~

102You can also save presets as profiles, then select them with `codex --profile <name>`:

~~103~~

104```

105[profiles.full_auto]

106approval_policy = "on-request"

107sandbox_mode = "workspace-write"

~~108~~

109[profiles.readonly_quiet]

110approval_policy = "never"

111sandbox_mode = "read-only"

112```

~~113~~

114### Test the sandbox locally

~~115~~

116To see what happens when a command runs under the Codex sandbox, use these Codex CLI commands:

~~117~~

118```

119# macOS

120codex sandbox macos [--full-auto] [--log-denials] [COMMAND]...

121# Linux

122codex sandbox linux [--full-auto] [COMMAND]...

123```

~~124~~

125The `sandbox` command is also available as `codex debug`, and the platform helpers have aliases (for example `codex sandbox seatbelt` and `codex sandbox landlock`).

~~126~~

127## OS-level sandbox

~~128~~

129Codex enforces the sandbox differently depending on your OS:

~~130~~

131- **macOS** uses Seatbelt policies and runs commands using `sandbox-exec` with a profile (`-p`) that corresponds to the `--sandbox` mode you selected.

132- **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`).

133- **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, you can enable an [experimental sandbox](https://developers.openai.com/codex/windows#windows-experimental-sandbox) implementation.

~~134~~

135If 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:

~~136~~

137```

138{

139 "chatgpt.runCodexInWindowsSubsystemForLinux": true

140}

141```

~~142~~

143This ensures the IDE extension inherits Linux sandbox semantics for commands, approvals, and filesystem access even when the host OS is Windows. Learn more in the [Windows setup guide](https://developers.openai.com/codex/windows).

~~144~~

145The native Windows sandbox is experimental and has important limitations. For example, it can’t prevent writes in directories where the `Everyone` SID already has write permissions (for example, world-writable folders). See the [Windows setup guide](https://developers.openai.com/codex/windows#windows-experimental-sandbox) for details and mitigation steps.

~~146~~

147When you run Linux in a containerized environment such as Docker, the sandbox may not work if the host or container configuration doesn’t support the required `Landlock` and `seccomp` features.

~~148~~

149In that case, configure your Docker container to provide the isolation you need, then run `codex` with `--sandbox danger-full-access` (or the `--dangerously-bypass-approvals-and-sandbox` flag) inside the container.

~~150~~

151## Version control

~~152~~

153Codex works best with a version control workflow:

~~154~~

155- Work on a feature branch and keep `git status` clean before delegating. This keeps Codex patches easier to isolate and revert.

156- Prefer patch-based workflows (for example, `git diff`/`git apply`) over editing tracked files directly. Commit frequently so you can roll back in small increments.

157- Treat Codex suggestions like any other PR: run targeted verification, review diffs, and document decisions in commit messages for auditing.

~~158~~

159## Monitoring and telemetry

~~160~~

161Codex supports opt-in monitoring via OpenTelemetry (OTel) to help teams audit usage, investigate issues, and meet compliance requirements without weakening local security defaults. Telemetry is off by default; enable it explicitly in your configuration.

~~162~~

163### Overview

~~164~~

165- Codex turns off OTel export by default to keep local runs self-contained.

166- When enabled, Codex emits structured log events covering conversations, API requests, SSE/WebSocket stream activity, user prompts (redacted by default), tool approval decisions, and tool results.

167- Codex tags exported events with `service.name` (originator), CLI version, and an environment label to separate dev/staging/prod traffic.

~~168~~

169### Enable OTel (opt-in)

~~170~~

171Add an `[otel]` block to your Codex configuration (typically `~/.codex/config.toml`), choosing an exporter and whether to log prompt text.

~~172~~

173```

174[otel]

175environment = "staging" # dev | staging | prod

176exporter = "none" # none | otlp-http | otlp-grpc

177log_user_prompt = false # redact prompt text unless policy allows

178```

~~179~~

180- `exporter = "none"` leaves instrumentation active but doesn’t send data anywhere.

181- To send events to your own collector, pick one of:

~~182~~

183```

184[otel]

185exporter = { otlp-http = {

186 endpoint = "https://otel.example.com/v1/logs",

187 protocol = "binary",

188 headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" }

189}}

190```

~~191~~

192```

193[otel]

194exporter = { otlp-grpc = {

195 endpoint = "https://otel.example.com:4317",

196 headers = { "x-otlp-meta" = "abc123" }

197}}

198```

~~199~~

200Codex batches events and flushes them on shutdown. Codex exports only telemetry produced by its OTel module.

~~201~~

202### Event categories

~~203~~

204Representative event types include:

~~205~~

206- `codex.conversation_starts` (model, reasoning settings, sandbox/approval policy)

207- `codex.api_request` (attempt, status/success, duration, and error details)

208- `codex.sse_event` (stream event kind, success/failure, duration, plus token counts on `response.completed`)

209- `codex.websocket_request` and `codex.websocket_event` (request duration plus per-message kind/success/error)

210- `codex.user_prompt` (length; content redacted unless explicitly enabled)

211- `codex.tool_decision` (approved/denied, source: configuration vs. user)

212- `codex.tool_result` (duration, success, output snippet)

~~213~~

214Associated OTel metrics (counter plus duration histogram pairs) include `codex.api_request`, `codex.sse_event`, `codex.websocket.request`, `codex.websocket.event`, and `codex.tool.call` (with corresponding `.duration_ms` instruments).

~~215~~

216For the full event catalog and configuration reference, see the [Codex configuration documentation on GitHub](https://github.com/openai/codex/blob/main/docs/config.md#otel).

~~217~~

218### Security and privacy guidance

~~219~~

220- Keep `log_user_prompt = false` unless policy explicitly permits storing prompt contents. Prompts can include source code and sensitive data.

221- Route telemetry only to collectors you control; apply retention limits and access controls aligned with your compliance requirements.

222- Treat tool arguments and outputs as sensitive. Favor redaction at the collector or SIEM when possible.

223- Review local data retention settings (for example, `history.persistence` / `history.max_bytes`) if you don’t want Codex to save session transcripts under `CODEX_HOME`. See [Advanced Config](https://developers.openai.com/codex/config-advanced#history-persistence) and [Configuration Reference](https://developers.openai.com/codex/config-reference).

224- If you run the CLI with network access turned off, OTel export can’t reach your collector. To export, allow network access in `workspace-write` mode for the OTel endpoint, or export from Codex cloud with the collector domain on your approved list.

225- Review events periodically for approval/sandbox changes and unexpected tool executions.

~~226~~

227OTel is optional and designed to complement, not replace, the sandbox and approval protections described above.

~~228~~

229## Managed configuration

~~230~~

231Enterprise admins can control local Codex behavior in two ways:

~~232~~

233- **Requirements**: admin-enforced constraints that users can’t override.

234- **Managed defaults**: starting values applied when Codex launches. Users can still change settings during a session; Codex reapplies managed defaults the next time it starts.

~~235~~

236### Admin-enforced requirements (requirements.toml)

~~237~~

238Requirements constrain security-sensitive settings (approval policy, sandbox mode, web search mode, and optionally which MCP servers you can enable). If a user explicitly selects a disallowed value (via `config.toml`, CLI flags, profiles, or in-session UI), Codex rejects the change. If a value isn’t explicitly set and the default conflicts with requirements, Codex falls back to a requirements-compliant default. If you configure an `mcp_servers` approved list, Codex enables an MCP server only when both its name and identity match an approved entry; otherwise, Codex turns it off.

~~239~~

240#### Locations

~~241~~

242- Linux/macOS (Unix): `/etc/codex/requirements.toml`

243- macOS MDM: preference domain `com.openai.codex`, key `requirements_toml_base64`

~~244~~

245#### Cloud requirements (Business and Enterprise)

~~246~~

247When you sign in with ChatGPT on a Business or Enterprise plan, Codex can also

248fetch admin-enforced requirements from the Codex service. This applies across

249Codex surfaces, including the TUI, `codex exec`, and `codex app-server`.

~~250~~

251Cloud requirements are currently best-effort. If the fetch fails or times out,

252Codex continues without the cloud layer.

~~253~~

254Requirements layer in this order (higher wins):

~~255~~

256- macOS managed preferences (MDM; highest precedence)

257- Cloud requirements (ChatGPT Business or Enterprise)

258- `/etc/codex/requirements.toml`

~~259~~

260Cloud requirements only fill unset requirement fields, so higher-precedence

261managed layers still win when both specify the same constraint.

~~262~~

263For backwards compatibility, Codex also interprets legacy `managed_config.toml` fields `approval_policy` and `sandbox_mode` as requirements (allowing only that single value).

~~264~~

265#### Example requirements.toml

~~266~~

267This example blocks `--ask-for-approval never` and `--sandbox danger-full-access` (including `--yolo`):

~~268~~

269```

270allowed_approval_policies = ["untrusted", "on-request"]

271allowed_sandbox_modes = ["read-only", "workspace-write"]

272```

~~273~~

274You can also constrain web search mode:

~~275~~

276```

277allowed_web_search_modes = ["cached"] # "disabled" remains implicitly allowed

278```

~~279~~

280`allowed_web_search_modes = []` effectively allows only `"disabled"`.

281For example, `allowed_web_search_modes = ["cached"]` prevents live web search even in `danger-full-access` sessions.

~~282~~

283#### Enforce command rules from requirements

~~284~~

285Admins can also enforce restrictive command rules from `requirements.toml`

286using a `[rules]` table. These rules merge with regular `.rules` files, and the

287most restrictive decision still wins.

~~288~~

289Unlike `.rules`, requirements rules must specify `decision`, and that decision

290must be `"prompt"` or `"forbidden"` (not `"allow"`).

~~291~~

292```

293[rules]

294prefix_rules = [

295 { pattern = [{ token = "rm" }], decision = "forbidden", justification = "Use git clean -fd instead." },

296 { pattern = [{ token = "git" }, { any_of = ["push", "commit"] }], decision = "prompt", justification = "Require review before mutating history." },

297]

298```

~~299~~

300To restrict which MCP servers Codex can enable, add an `mcp_servers` approved list. For stdio servers, match on `command`; for streamable HTTP servers, match on `url`:

~~301~~

302```

303[mcp_servers.docs]

304identity = { command = "codex-mcp" }

~~305~~

306[mcp_servers.remote]

307identity = { url = "https://example.com/mcp" }

308```

~~309~~

310If `mcp_servers` is present but empty, Codex disables all MCP servers.

~~311~~

312### Managed defaults (managed\_config.toml)

~~313~~

314Managed defaults merge on top of a user’s local `config.toml` and take precedence over any CLI `--config` overrides, setting the starting values when Codex launches. Users can still change those settings during a session; Codex reapplies managed defaults the next time it starts.

~~315~~

316Make sure your managed defaults meet your requirements; Codex rejects disallowed values.

~~317~~

318#### Precedence and layering

~~319~~

320Codex assembles the effective configuration in this order (top overrides bottom):

~~321~~

322- Managed preferences (macOS MDM; highest precedence)

323- `managed_config.toml` (system/managed file)

324- `config.toml` (user’s base configuration)

~~325~~

326CLI `--config key=value` overrides apply to the base, but managed layers override them. This means each run starts from the managed defaults even if you provide local flags.

~~327~~

328Cloud requirements affect the requirements layer (not managed defaults). See

329[Admin-enforced requirements](https://developers.openai.com/codex/security#admin-enforced-requirements-requirementstoml)

330for their precedence.

~~331~~

332#### Locations

~~333~~

334- Linux/macOS (Unix): `/etc/codex/managed_config.toml`

335- Windows/non-Unix: `~/.codex/managed_config.toml`

~~336~~

337If the file is missing, Codex skips the managed layer.

~~338~~

339#### macOS managed preferences (MDM)

~~340~~

341On macOS, admins can push a device profile that provides base64-encoded TOML payloads at:

~~342~~

343- Preference domain: `com.openai.codex`

344- Keys:

345 - `config_toml_base64` (managed defaults)

346 - `requirements_toml_base64` (requirements)

~~347~~

348Codex parses these “managed preferences” payloads as TOML and applies them with the highest precedence.

~~349~~

350### MDM setup workflow

~~351~~

352Codex honors standard macOS MDM payloads, so you can distribute settings with tooling like `Jamf Pro`, `Fleet`, or `Kandji`. A lightweight deployment looks like:

~~353~~

3541. Build the managed payload TOML and encode it with `base64` (no wrapping).

3552. Drop the string into your MDM profile under the `com.openai.codex` domain at `config_toml_base64` (managed defaults) or `requirements_toml_base64` (requirements).

3563. Push the profile, then ask users to restart Codex and confirm the startup config summary reflects the managed values.

3574. When revoking or changing policy, update the managed payload; the CLI reads the refreshed preference the next time it launches.

~~358~~

359Avoid embedding secrets or high-churn dynamic values in the payload. Treat the managed TOML like any other MDM setting under change control.

~~360~~

361### Example managed\_config.toml

~~362~~

363```

364# Set conservative defaults

365approval_policy = "on-request"

366sandbox_mode = "workspace-write"

~~367~~

368[sandbox_workspace_write]

369network_access = false # keep network disabled unless explicitly allowed

~~370~~

371[otel]

372environment = "prod"

373exporter = "otlp-http" # point at your collector

374log_user_prompt = false # keep prompts redacted

375# exporter details live under exporter tables; see Monitoring and telemetry above

376```

~~377~~

378### Recommended guardrails

~~379~~

380- Prefer `workspace-write` with approvals for most users; reserve full access for controlled containers.

381- Keep `network_access = false` unless your security review allows a collector or domains required by your workflows.

382- Use managed configuration to pin OTel settings (exporter, environment), but keep `log_user_prompt = false` unless your policy explicitly allows storing prompt contents.

383- Periodically audit diffs between local `config.toml` and managed policy to catch drift; managed layers should win over local flags and files.

security/faq.md +104 −0 added

Details

1# FAQ

3## Getting started

5### What is Codex Security?

7Software security remains one of the hardest and most important problems in engineering. Codex Security is an LLM-driven security analysis toolkit that inspects source code and returns structured, ranked vulnerability findings with proposed patches. It helps developers and security teams discover and fix security issues at scale.

9### Why does it matter?

11Software is foundational to modern industry and society, and vulnerabilities create systemic risk. Codex Security supports a defender-first workflow by continuously identifying likely issues, validating them when possible, and proposing fixes. That helps teams improve security without slowing development.

13### What business problem does Codex Security solve?

15Codex Security shortens the path from a suspected issue to a confirmed, reproducible finding with evidence and a proposed patch. That reduces triage load and cuts false positives compared with traditional scanners alone.

17### How does Codex Security work?

19Codex Security runs analysis in an ephemeral, isolated container and temporarily clones the target repository. It performs code-level analysis and returns structured findings with a description, file and location, criticality, root cause, and a suggested remediation.

21For findings that include verification steps, the system executes proposed commands or tests in the same sandbox, records success or failure, exit codes, stdout, stderr, test results, and any generated diffs or artifacts, and attaches that output as evidence for review.

23### Does it replace SAST?

25No. Codex Security complements SAST. It adds semantic, LLM-based reasoning and automated validation, while existing SAST tools still provide broad deterministic coverage.

27## Features

29### What is the analysis pipeline?

31Codex Security follows a staged pipeline:

331. **Analysis** builds a threat model for the repository.

342. **Commit scanning** reviews merged commits and repository history for likely issues.

353. **Validation** tries to reproduce likely vulnerabilities in a sandbox to reduce false positives.

364. **Patching** integrates with Codex to propose patches that reviewers can inspect before opening a PR.

38It works alongside engineers in GitHub, Codex, and standard review workflows.

40### What languages are supported?

42Codex Security is language-agnostic. In practice, performance depends on the model's reasoning ability for the language and framework used by the repository.

44### What outputs do I get after the scan completes?

46You get ranked findings with criticality, validation status, and a proposed patch when one is available. Findings can also include crash output, reproduction evidence, call-path context, and related annotations.

48### How is customer code isolated?

50Each analysis and validation job runs in an ephemeral Codex container with session-scoped tools. Artifacts are extracted for review, and the container is torn down after the job completes.

52### Does Codex Security auto-apply patches?

54No. The proposed patch is a recommended remediation. Users can review it and push it as a PR to GitHub from the findings UI, but Codex Security does not auto-apply changes to the repository.

56### Does the project need to be built for scanning?

58No. Codex Security can produce findings from repository and commit context without a compile step. During auto-validation, it may try to build the project inside the container if that helps reproduce the issue. For environment setup details, see [Codex cloud environments](https://developers.openai.com/codex/cloud/environments).

60### How does Codex Security reduce false positives and avoid broken patches?

62Codex Security uses two stages. First, the model ranks likely issues. Then auto-validation tries to reproduce each issue in a clean container. Findings that successfully reproduce are marked as validated, which helps reduce false positives before human review.

64### How long do initial scans take, and what happens after that?

66Initial scan time depends on repository size, build time, and how many findings proceed to validation. For some repositories, scans can take several hours. For larger repositories, they can take multiple days. Later scans are usually faster because they focus on new commits and incremental changes.

68### What is a threat model?

70A threat model is the scan-time security context for a repository. It combines a concise project overview with attack-surface details such as entry points, trust boundaries, auth assumptions, and risky components. For more detail, see [Improving the threat model](https://developers.openai.com/codex/security/threat-model).

72### How is a threat model generated?

74Codex Security prompts the model to summarize the repository architecture and security entry points, classify the repository type, run specialized extractors, and merge the results into a project overview or threat model artifact used throughout the scan.

76### Does it replace manual security review?

78No. Codex Security accelerates review and helps rank findings, but it does not replace code-level validation, exploitability checks, or human threat assessment.

80### Can I edit the threat model?

82Yes. Codex Security creates the initial threat model, and you can update it as the architecture, risks, and business context change. For the editing workflow, see [Improving the threat model](https://developers.openai.com/codex/security/threat-model).

84### Do I need to configure a scan before using threat modeling?

86Yes. Threat-model guidance is tied to how and what you scan, so you need to configure the repository first. See [Codex Security setup](https://developers.openai.com/codex/security/setup).

88### What does the proposed patch contain?

90The proposed patch contains a minimal actionable diff with filename and line context when a remediation can be generated for the finding.

92### Does the patch directly modify my PR branch?

94No. The workflow generates a diff, patch file, or suggested change for maintainers and reviewers to inspect before applying.

96## Validation

98### What is auto-validation?

100Auto-validation is the phase that tries to reproduce a suspected issue in an isolated container. It records whether reproduction succeeded or failed and captures logs, commands, and related artifacts as evidence.

101

102### What happens if validation fails?

103

104The finding remains unvalidated. Logs and reports still capture what was attempted so engineers can retry, investigate further, or adjust the reproduction steps.

security/setup.md +97 −0 added

Details

1# Codex Security setup

3This page walks you from initial access to reviewed findings and remediation pull requests in Codex Security.

5Confirm you've set up Codex Cloud first. If not, see [Codex

6 Cloud](https://developers.openai.com/codex/cloud) to get started.

8## 1. Access and environment

10Codex Security scans GitHub repositories connected through [Codex Cloud](https://developers.openai.com/codex/cloud).

12- Confirm your workspace has access to Codex Security.

13- Confirm the repository you want to scan is available in Codex Cloud.

15Go to [Codex environments](https://chatgpt.com/codex/settings/environments) and check whether the repository already has an environment. If it doesn't, create one there before continuing.

17[Open environments](https://chatgpt.com/codex/settings/environments)

19![Codex environments](/_astro/create_environment.M-EPszPH.png)

21## 2. New security scan

23After the environment exists, go to [Create a security scan](https://chatgpt.com/codex/security/scans/new) and choose the repository you just connected.

25[Create a security scan](https://chatgpt.com/codex/security/scans/new)

27Codex Security scans repositories from newest commits backward first. It uses this to build and refresh scan context as new commits come in.

29To configure a repository:

311. Select the GitHub organization.

322. Select the repository.

333. Select the branch you want to scan.

344. Select the environment.

355. Choose a **history window**. Longer windows provide more context, but backfill takes longer.

366. Click **Create**.

38![Create a security scan](/_astro/create_scan.mEjmf4U_.png)

40## 3. Initial scans can take a while

42When you create the scan, Codex Security first runs a commit-level security pass across the selected history window.

43The initial backfill can take a few hours, especially for larger repositories or longer windows.

44If findings aren't visible right away, this is expected. Wait for the initial scan to finish before opening a ticket or troubleshooting.

46Initial scan setup is automatic and thorough. This can take a few hours. Don’t

47 be alarmed if the first set of findings is delayed.

49## 4. Review scans and improve the threat model

51[Review scans](https://chatgpt.com/codex/security/scans)

53![Threat model editor in Codex Security](/_astro/review_threat_model.JTLMQEmx.png)

55When the initial scan finishes, open the scan and review the threat model that was generated.

56After initial findings appear, update the threat model so it matches your architecture, trust boundaries, and business context.

57This helps Codex Security rank issues for your team.

59If you want scan results to change, you can edit the threat model with your

60 updated scope, priorities, and assumptions.

62After initial findings appear, revisit the model so scan guidance stays aligned with current priorities.

63Keeping it current helps Codex Security produce better suggestions.

65For a deeper explanation of threat models and how they affect criticality and triage, see [Improving the threat model](https://developers.openai.com/codex/security/threat-model).

67## 5. Review findings and patch

69After the initial backfill completes, review findings from the **Findings** view.

71[Open findings](https://chatgpt.com/codex/security/findings)

73You can use two views:

75- **Recommended Findings**: an evolving top 10 list of the most critical issues in the repo

76- **All Findings**: a sortable, filterable table of findings across the repository

78![Recommended findings view](https://developers.openai.com/codex/security/images/aardvark_recommended_findings.png)

80Click a finding to open its detail page, which includes:

82- a concise description of the issue

83- key metadata such as commit details and file paths

84- contextual reasoning about impact

85- relevant code excerpts

86- call-path or data-flow context when available

87- validation steps and validation output

89You can review each finding and create a PR directly from the finding detail page.

91[Review findings and create a PR](https://chatgpt.com/codex/security/findings)

93## Related docs

95- [Codex Security](https://developers.openai.com/codex/security) gives the product overview.

96- [FAQ](https://developers.openai.com/codex/security/faq) covers common questions.

97- [Improving the threat model](https://developers.openai.com/codex/security/threat-model) explains how to improve scan context and finding prioritization.

security/threat-model.md +40 −0 added

Details

1# Improving the threat model

3Learn what a threat model is and how editing it improves Codex Security's suggestions.

5## What a threat model is

7A threat model is a short security summary of how your repository works. In Codex Security, you edit it as a `project overview`, and the system uses it as scan context for future scans, prioritization, and review.

9Codex Security creates the first draft from the code. If the findings feel off, this is the first thing to edit.

11A useful threat model calls out:

13- entry points and untrusted inputs

14- trust boundaries and auth assumptions

15- sensitive data paths or privileged actions

16- the areas your team wants reviewed first

18For example:

20> Public API for account changes. Accepts JSON requests and file uploads. Uses an internal auth service for identity checks and writes billing changes through an internal service. Focus review on auth checks, upload parsing, and service-to-service trust boundaries.

22That gives Codex Security a better starting point for future scans and finding prioritization.

24## Improving and revisiting the threat model

26If you want to improve the results, edit the threat model first. Use it when findings are missing the areas you care about or showing up in places you don't expect. The threat model changes future scan context.

28Some users copy the current threat model into Codex, have a conversation to

29 improve it based on the areas they want reviewed more closely, and then paste

30 the updated version back into the web UI.

32### Where to edit

34To review or update the threat model, go to [Codex Security scans](https://chatgpt.com/codex/security/scans), open the repository, and click **Edit**.

36## Related docs

38- [Codex Security setup](https://developers.openai.com/codex/security/setup) covers repository setup and findings review.

39- [Codex Security](https://developers.openai.com/codex/security) gives the product overview.

40- [FAQ](https://developers.openai.com/codex/security/faq) covers common questions.

skills.md +2 −2

Details

67 67

68## Install skills68## Install skills

69 69

~~70To install skills beyond the built-ins, use `$skill-installer`:~~70To install skills beyond the built-ins, use `$skill-installer`. For example, to install the `$linear` skill:

71 71

72```bash72```bash

~~73$skill-installer install the linear skill from the .experimental folder~~73$skill-installer linear

74```74```

75 75

76You can also prompt the installer to download skills from other repositories. Codex detects newly installed skills automatically; if one doesn’t appear, restart Codex.76You can also prompt the installer to download skills from other repositories. Codex detects newly installed skills automatically; if one doesn’t appear, restart Codex.

speed.md +24 −0 added

Details

1# Speed

3## Fast mode

5Codex offers the ability to increase the speed of the model for increased

6credit consumption.

8Fast mode is currently supported on GPT-5.4. When enabled, speed is increased

9by 1.5x and credits are consumed at a 2x rate.

11Enable it by typing `/fast`. It’s available in Codex IDE Extensions, Codex

12CLI, and the Codex app when you sign in with ChatGPT. With an API key, Codex

13uses standard API pricing instead and you can’t use `/fast`.

15[

16Your browser does not support the video tag.

17](/videos/codex/fast-mode-demo.mp4)

19## Codex-Spark

21GPT-5.3-Codex-Spark is a separate fast, less-capable Codex model optimized for near-instant, real-time coding iteration. Unlike fast mode, which speeds up GPT-5.4 at a higher credit rate,

22Codex-Spark is its own model choice and has its own usage limits.

24During research preview Codex-Spark is only available for ChatGPT Pro subscribers.

windows.md +35 −24

Details

1# Windows1# Windows

2 2

3The easiest way to use Codex on Windows is to [set up the IDE extension](https://developers.openai.com/codex/ide) or [install the CLI](https://developers.openai.com/codex/cli) and run it from PowerShell.3The easiest way to use Codex on Windows is to use the [Codex app](https://developers.openai.com/codex/app/windows). You can also [set up the IDE extension](https://developers.openai.com/codex/ide) or [install the CLI](https://developers.openai.com/codex/cli) and run it from PowerShell.

4 4

5When you run Codex natively on Windows, the agent mode uses an experimental Windows sandbox to block filesystem writes outside the working folder and prevent network access without your explicit approval. [Learn more below](#windows-experimental-sandbox).5[![](/images/codex/codex-banner-icon.webp)

6 6

7Instead, you can use [Windows Subsystem for Linux](https://learn.microsoft.com/en-us/windows/wsl/install) (WSL2). WSL2 gives you a Linux shell, Unix-style semantics, and tooling that match many tasks that models see in training.7Use the Codex app on Windows

9Work across projects, run parallel agent threads, and review results in one place with the native Windows app.](https://developers.openai.com/codex/app/windows)

11When you run Codex natively on Windows, agent mode uses a [Windows sandbox](#windows-sandbox) to block filesystem writes outside the working folder and prevent network access without your explicit approval. [Learn more below](#windows-sandbox).

13If you prefer to have Codex use [Windows Subsystem for Linux](https://learn.microsoft.com/en-us/windows/wsl/install) (WSL2), [read the instructions](#windows-subsystem-for-linux) below.

15## Windows sandbox

17Native Windows sandbox support includes two modes that you can configure in `config.toml`:

19```

20[windows]

21sandbox = "unelevated" # or "elevated"

22```

24How `elevated` mode works:

26- Uses a Restricted Token approach with filesystem ACLs to limit which files the sandbox can write to.

27- Runs commands as a dedicated Windows Sandbox User.

28- Limits network access by installing Windows Firewall rules.

30### Grant sandbox read access

32When a command fails because the Windows sandbox can't read a directory, use:

34```text

35/sandbox-add-read-dir C:\absolute\directory\path

36```

38The path must be an existing absolute directory. After the command succeeds, later commands that run in the sandbox can read that directory during the current session.

8 39

9## Windows Subsystem for Linux40## Windows Subsystem for Linux

10 41

81 ```112 ```

82- If you need Windows access to files, they’re under `\wsl$\Ubuntu\home<user>` in Explorer.113- If you need Windows access to files, they’re under `\wsl$\Ubuntu\home<user>` in Explorer.

83 114

~~84## Windows experimental sandbox~~115## Troubleshooting and FAQ

~~86The Windows sandbox support is experimental. How it works:~~

~~88- Launches commands inside a restricted token derived from an AppContainer profile.~~

~~89- Grants only specifically requested filesystem capabilities by attaching capability security identifiers to that profile.~~

~~90- Disables outbound network access by overriding proxy-related environment variables and inserting stub executables for common network tools.~~

92Its primary limitation is that it can’t prevent file writes, deletions, or creations in any directory where the Everyone SID already has write permissions (for example, world-writable folders). When using the Windows sandbox, Codex scans for folders where Everyone has write access and recommends that you remove that access.

~~94### Grant sandbox read access~~

~~96When a command fails because the Windows sandbox can't read a directory, use:~~

~~98```text~~

~~99/sandbox-add-read-dir C:\absolute\directory\path~~

100```

~~101~~

102The path must be an existing absolute directory. After the command succeeds, later commands that run in the sandbox can read that directory during the current session.

~~103~~

104### Troubleshooting and FAQ

105 116

106#### Installed extension, but it’s unresponsive117#### Installed extension, but it’s unresponsive

107 118

OpenAI - Codex Docs Changes 2026-02-20 12:16 UTC → 2026-03-08 00:35 UTC