OpenAI - Codex Docs Changes 2026-02-19 20:37 UTC → 2026-04-08 00:40 UTC

1# Agent approvals & security

2 

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

4 

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).

8 

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.

10 

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).

13For a broader enterprise security overview, see the [Codex security white paper](https://trust.openai.com/?itemUid=382f924d-54f3-43a8-a9df-c39e6c959958&source=click).

14 

15## Sandbox and approvals

16 

17Codex security controls come from two layers that work together:

18 

19- **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.

20- **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).

21 

22Codex uses different sandbox modes depending on where you run it:

23 

24- **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.

25- **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.

26 

27In the `Auto` preset (for example, `--full-auto`), Codex can read files, make edits, and run commands in the working directory automatically.

28 

29Codex 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.

30 

31Codex 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 

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

34 

35For Codex cloud, see [agent internet access](https://developers.openai.com/codex/cloud/internet-access) to enable full internet access or a domain allow list.

36 

37For 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 

39```toml

40[sandbox_workspace_write]

41network_access = true

42```

43 

44You 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 

46```toml

47web_search = "cached" # default

48# web_search = "disabled"

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

50```

51 

52Use caution when enabling network access or web search in Codex. Prompt injection can cause the agent to fetch and follow untrusted instructions.

53 

54## Defaults and recommendations

55 

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

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

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

59- 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`).

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

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

62- You can set these explicitly:

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

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

65 

66### Protected paths in writable roots

67 

68In the default `workspace-write` sandbox policy, writable roots still include protected paths:

69 

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

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

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

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

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

75 

76### Run without approval prompts

77 

78You can disable approval prompts with `--ask-for-approval never` or `-a never` (shorthand).

79 

80This 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.

81 

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

83 

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

85 

86### Common sandbox and approval combinations

87 

88| Intent | Flags | Effect |

89| ----------------------------------------------------------------- | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------ |

90| 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. |

91| 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. |

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

93| 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. |

94| 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 

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

97 

98With `--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 

100#### Configuration in `config.toml`

101 

102For 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).

103 

104```toml

105# Always ask for approval mode

106approval_policy = "untrusted"

107sandbox_mode = "read-only"

108allow_login_shell = false # optional hardening: disallow login shells for shell-based tools

109 

110# Optional: Allow network in workspace-write mode

111[sandbox_workspace_write]

112network_access = true

113 

114# Optional: granular approval policy

115# approval_policy = { granular = {

116# sandbox_approval = true,

117# rules = true,

118# mcp_elicitations = true,

119# request_permissions = false,

120# skill_approval = false

121# } }

122```

123 

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

125 

126```toml

127[profiles.full_auto]

128approval_policy = "on-request"

129sandbox_mode = "workspace-write"

130 

131[profiles.readonly_quiet]

132approval_policy = "never"

133sandbox_mode = "read-only"

134```

135 

136### Test the sandbox locally

137 

138To see what happens when a command runs under the Codex sandbox, use these Codex CLI commands:

139 

140```bash

141# macOS

142codex sandbox macos [--full-auto] [--log-denials] [COMMAND]...

143# Linux

144codex sandbox linux [--full-auto] [COMMAND]...

145```

146 

147The `sandbox` command is also available as `codex debug`, and the platform helpers have aliases (for example `codex sandbox seatbelt` and `codex sandbox landlock`).

148 

149## OS-level sandbox

150 

151Codex enforces the sandbox differently depending on your OS:

152 

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

154- **Linux** uses the bubblewrap pipeline plus `seccomp` by default. `use_legacy_landlock` is available when you need the older path. In managed proxy mode, the default bubblewrap pipeline routes egress through a proxy-only bridge and fails closed if it cannot build valid loopback proxy routes.

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

156 

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

158 

159```json

160{

161 "chatgpt.runCodexInWindowsSubsystemForLinux": true

162}

163```

164 

165This 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).

166 

167When running natively on Windows, configure the native sandbox mode in `config.toml`:

168 

169```toml

170[windows]

171sandbox = "unelevated" # or "elevated"

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

173```

174 

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

176 

177When 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.

178 

179In 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.

180 

181## Version control

182 

183Codex works best with a version control workflow:

184 

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

186- 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.

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

188 

189## Monitoring and telemetry

190 

191Codex 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.

192 

193### Overview

194 

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

196- 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.

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

198 

199### Enable OTel (opt-in)

200 

201Add an `[otel]` block to your Codex configuration (typically `~/.codex/config.toml`), choosing an exporter and whether to log prompt text.

202 

203```toml

204[otel]

205environment = "staging" # dev | staging | prod

206exporter = "none" # none | otlp-http | otlp-grpc

207log_user_prompt = false # redact prompt text unless policy allows

208```

209 

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

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

212 

213```toml

214[otel]

215exporter = { otlp-http = {

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

217 protocol = "binary",

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

219}}

220```

221 

222```toml

223[otel]

224exporter = { otlp-grpc = {

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

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

227}}

228```

229 

230Codex batches events and flushes them on shutdown. Codex exports only telemetry produced by its OTel module.

231 

232### Event categories

233 

234Representative event types include:

235 

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

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

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

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

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

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

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

243 

244Associated 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).

245 

246For 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).

247 

248### Security and privacy guidance

249 

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

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

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

253- 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).

254- 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.

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

256 

257OTel is optional and designed to complement, not replace, the sandbox and approval protections described above.

258 

259## Managed configuration

260 

261Enterprise 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.

1# Codex app1# Codex app

2 2 

3Your Codex command center

4 

5The Codex app is a focused desktop experience for working on Codex threads in parallel, with built-in worktree support, automations, and Git functionality.3The Codex app is a focused desktop experience for working on Codex threads in parallel, with built-in worktree support, automations, and Git functionality.

6 4 

7ChatGPT 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).

8 6 

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

10 8 

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

12 10 

13## Getting started11## Getting started

14 12 

16 14 

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

18 16 

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

20 18 

21 [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)

22 20 

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

242. Open Codex and sign in222. Open Codex and sign in

25 23 

26 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.

38 36 

39 You can ask Codex anything about the project or your computer in general. Here are some examples:37 You can ask Codex anything about the project or your computer in general. Here are some examples:

40 38 

41 ![](https://developers.openai.com/codex/colorcons/brain.png)Tell me about this projectCopied![](https://developers.openai.com/codex/colorcons/gamepad.png)Build a classic Snake game in this repo.Copied![](https://developers.openai.com/codex/colorcons/search.png)Find and fix bugs in my codebase with minimal, high-confidence changes.Copied39- Tell me about this project

40- Build a classic Snake game in this repo.

41- Find and fix bugs in my codebase with minimal, high-confidence changes.

42 42 

43 If you need more inspiration, check out the [explore section](https://developers.openai.com/codex/explore).43 If you need more inspiration, check out the [explore section](https://developers.openai.com/codex/explore).

44 If you're new to Codex, read the [best practices guide](https://developers.openai.com/codex/learn/best-practices).

44 45 

45---46---

46 47 

69---70---

70 71 

71Need help? Visit the [troubleshooting guide](https://developers.openai.com/codex/app/troubleshooting).72Need help? Visit the [troubleshooting guide](https://developers.openai.com/codex/app/troubleshooting).

72 

73[Next

74 

75Features](https://developers.openai.com/codex/app/features)

1# Codex App Server1# Codex App Server

2 2 

3Embed Codex into your product with the app-server protocol

4 

5Codex app-server is the interface Codex uses to power rich clients (for example, the Codex VS Code extension). Use it when you want a deep integration inside your own product: authentication, conversation history, approvals, and streamed agent events. The app-server implementation is open source in the Codex GitHub repository ([openai/codex/codex-rs/app-server](https://github.com/openai/codex/tree/main/codex-rs/app-server)). See the [Open Source](https://developers.openai.com/codex/open-source) page for the full list of open-source Codex components.3Codex app-server is the interface Codex uses to power rich clients (for example, the Codex VS Code extension). Use it when you want a deep integration inside your own product: authentication, conversation history, approvals, and streamed agent events. The app-server implementation is open source in the Codex GitHub repository ([openai/codex/codex-rs/app-server](https://github.com/openai/codex/tree/main/codex-rs/app-server)). See the [Open Source](https://developers.openai.com/codex/open-source) page for the full list of open-source Codex components.

6 4 

7If you are automating jobs or running Codex in CI, use the5If you are automating jobs or running Codex in CI, use the

23Requests include `method`, `params`, and `id`:21Requests include `method`, `params`, and `id`:

24 22 

25```json23```json

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

27```25```

28 26 

29Responses echo the `id` with either `result` or `error`:27Responses echo the `id` with either `result` or `error`:

101 },99 },

102});100});

103send({ method: "initialized", params: {} });101send({ method: "initialized", params: {} });

104send({ method: "thread/start", id: 1, params: { model: "gpt-5.1-codex" } });102send({ method: "thread/start", id: 1, params: { model: "gpt-5.4" } });

105```103```

106 104 

107## Core primitives105## Core primitives

118- **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.

119- **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.

120- **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.

121- **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.

122- **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.

123 121 

124## Initialization122## Initialization

125 123 

126Clients must send a single `initialize` request per transport connection before invoking any other method on that connection, then acknowledge with an `initialized` notification. Requests sent before initialization receive a `Not initialized` error, and repeated `initialize` calls on the same connection return `Already initialized`.124Clients must send a single `initialize` request per transport connection before invoking any other method on that connection, then acknowledge with an `initialized` notification. Requests sent before initialization receive a `Not initialized` error, and repeated `initialize` calls on the same connection return `Already initialized`.

127 125 

128The server returns the user agent string it will present to upstream services. Set `clientInfo` to identify your integration.126The server returns the user agent string it will present to upstream services plus `platformFamily` and `platformOs` values that describe the runtime target. Set `clientInfo` to identify your integration.

129 127 

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

131 129 

161 },159 },

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

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

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

165 "codex/event/session_configured",

166 "item/agentMessage/delta"

167 ]

168 }163 }

169 }164 }

170}165}

203- `thread/start` - create a new thread; emits `thread/started` and automatically subscribes you to turn/item events for that thread.198- `thread/start` - create a new thread; emits `thread/started` and automatically subscribes you to turn/item events for that thread.

204- `thread/resume` - reopen an existing thread by id so later `turn/start` calls append to it.199- `thread/resume` - reopen an existing thread by id so later `turn/start` calls append to it.

205- `thread/fork` - fork a thread into a new thread id by copying stored history; emits `thread/started` for the new thread.200- `thread/fork` - fork a thread into a new thread id by copying stored history; emits `thread/started` for the new thread.

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

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

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

209- `thread/archive` - move a thread’s log file into the archived directory; returns `{}` on success.204- `thread/name/set` - set or update a thread's user-facing name for a loaded thread or a persisted rollout; emits `thread/name/updated`.

210- `thread/unarchive` - restore an archived thread rollout back into the active sessions directory; returns the restored `thread`.205- `thread/archive` - move a thread's log file into the archived directory; returns `{}` on success and emits `thread/archived`.

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

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

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

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

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

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."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."

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

226- `config/mcpServer/reload` - reload MCP server configuration from disk and queue a refresh for loaded threads.229- `config/mcpServer/reload` - reload MCP server configuration from disk and queue a refresh for loaded threads.

227- `mcpServerStatus/list` - list MCP servers, tools, resources, and auth status (cursor + limit pagination).230- `mcpServerStatus/list` - list MCP servers, tools, resources, and auth status (cursor + limit pagination).

228- `feedback/upload` - submit a feedback report (classification + optional reason/logs + conversation id).231- `windowsSandbox/setupStart` - start Windows sandbox setup for `elevated` or `unelevated` mode; returns quickly and later emits `windowsSandbox/setupCompleted`.

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

229- `config/read` - fetch the effective configuration on disk after resolving configuration layering.233- `config/read` - fetch the effective configuration on disk after resolving configuration layering.

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

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

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

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

232- `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).238- `configRequirements/read` - fetch requirements from `requirements.toml` and/or MDM, including allow-lists, pinned `featureRequirements`, and residency/network requirements (or `null` if you haven't set any up).

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

233 240 

234## Models241## Models

235 242 

241{ "method": "model/list", "id": 6, "params": { "limit": 20, "includeHidden": false } }248{ "method": "model/list", "id": 6, "params": { "limit": 20, "includeHidden": false } }

242{ "id": 6, "result": {249{ "id": 6, "result": {

243 "data": [{250 "data": [{

244 "id": "gpt-5.2-codex",251 "id": "gpt-5.4",

245 "model": "gpt-5.2-codex",252 "model": "gpt-5.4",

246 "upgrade": "gpt-5.3-codex",253 "displayName": "GPT-5.4",

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

248 "hidden": false,254 "hidden": false,

249 "defaultReasoningEffort": "medium",255 "defaultReasoningEffort": "medium",

250 "reasoningEffort": [{256 "supportedReasoningEfforts": [{

251 "effort": "low",257 "reasoningEffort": "low",

252 "description": "Lower latency"258 "description": "Lower latency"

253 }],259 }],

254 "inputModalities": ["text", "image"],260 "inputModalities": ["text", "image"],

261 267 

262Each model entry can include:268Each model entry can include:

263 269 

264- `reasoningEffort` - supported effort options for the model.270- `supportedReasoningEfforts` - supported effort options for the model.

265- `defaultReasoningEffort` - suggested default effort for clients.271- `defaultReasoningEffort` - suggested default effort for clients.

266- `upgrade` - optional recommended upgrade model id for migration prompts in clients.272- `upgrade` - optional recommended upgrade model id for migration prompts in clients.

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

267- `hidden` - whether the model is hidden from the default picker list.274- `hidden` - whether the model is hidden from the default picker list.

268- `inputModalities` - supported input types for the model (for example `text`, `image`).275- `inputModalities` - supported input types for the model (for example `text`, `image`).

269- `supportsPersonality` - whether the model supports personality-specific instructions such as `/personality`.276- `supportsPersonality` - whether the model supports personality-specific instructions such as `/personality`.

301- `thread/list` supports cursor pagination plus `modelProviders`, `sourceKinds`, `archived`, and `cwd` filtering.308- `thread/list` supports cursor pagination plus `modelProviders`, `sourceKinds`, `archived`, and `cwd` filtering.

302- `thread/loaded/list` returns the thread IDs currently in memory.309- `thread/loaded/list` returns the thread IDs currently in memory.

303- `thread/archive` moves the thread's persisted JSONL log into the archived directory.310- `thread/archive` moves the thread's persisted JSONL log into the archived directory.

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

304- `thread/unarchive` restores an archived thread rollout back into the active sessions directory.312- `thread/unarchive` restores an archived thread rollout back into the active sessions directory.

305- `thread/compact/start` triggers compaction and returns `{}` immediately.313- `thread/compact/start` triggers compaction and returns `{}` immediately.

306- `thread/rollback` drops the last N turns from the in-memory context and records a rollback marker in the thread's persisted JSONL log.314- `thread/rollback` drops the last N turns from the in-memory context and records a rollback marker in the thread's persisted JSONL log.

311 319 

312```json320```json

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

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

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

316 "approvalPolicy": "never",324 "approvalPolicy": "never",

317 "sandbox": "workspaceWrite",325 "sandbox": "workspaceWrite",

318 "personality": "friendly"326 "personality": "friendly",

327 "serviceName": "my_app_server_client"

319} }328} }

320{ "id": 10, "result": {329{ "id": 10, "result": {

321 "thread": {330 "thread": {

322 "id": "thr_123",331 "id": "thr_123",

323 "preview": "",332 "preview": "",

333 "ephemeral": false,

324 "modelProvider": "openai",334 "modelProvider": "openai",

325 "createdAt": 1730910000335 "createdAt": 1730910000

326 }336 }

328{ "method": "thread/started", "params": { "thread": { "id": "thr_123" } } }338{ "method": "thread/started", "params": { "thread": { "id": "thr_123" } } }

329```339```

330 340 

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

342 

331To 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`:343To 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`:

332 344 

333```json345```json

335 "threadId": "thr_123",347 "threadId": "thr_123",

336 "personality": "friendly"348 "personality": "friendly"

337} }349} }

338{ "id": 11, "result": { "thread": { "id": "thr_123" } } }350{ "id": 11, "result": { "thread": { "id": "thr_123", "name": "Bug bash notes", "ephemeral": false } } }

339```351```

340 352 

341Resuming a thread doesn't update `thread.updatedAt` (or the rollout file's modified time) by itself. The timestamp updates when you start a turn.353Resuming a thread doesn't update `thread.updatedAt` (or the rollout file's modified time) by itself. The timestamp updates when you start a turn.

354{ "method": "thread/started", "params": { "thread": { "id": "thr_456" } } }366{ "method": "thread/started", "params": { "thread": { "id": "thr_456" } } }

355```367```

356 368 

369When 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.

370 

357### Read a stored thread (without resuming)371### Read a stored thread (without resuming)

358 372 

359Use `thread/read` when you want stored thread data but don't want to resume the thread or subscribe to its events.373Use `thread/read` when you want stored thread data but don't want to resume the thread or subscribe to its events.

360 374 

361- `includeTurns` - when `true`, the response includes the thread's turns; when `false` or omitted, you get the thread summary only.375- `includeTurns` - when `true`, the response includes the thread's turns; when `false` or omitted, you get the thread summary only.

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

362 377 

363```json378```json

364{ "method": "thread/read", "id": 19, "params": { "threadId": "thr_123", "includeTurns": true } }379{ "method": "thread/read", "id": 19, "params": { "threadId": "thr_123", "includeTurns": true } }

365{ "id": 19, "result": { "thread": { "id": "thr_123", "turns": [] } } }380{ "id": 19, "result": { "thread": { "id": "thr_123", "name": "Bug bash notes", "ephemeral": false, "status": { "type": "notLoaded" }, "turns": [] } } }

366```381```

367 382 

368Unlike `thread/resume`, `thread/read` doesn't load the thread into memory or emit `thread/started`.383Unlike `thread/resume`, `thread/read` doesn't load the thread into memory or emit `thread/started`.

402} }417} }

403{ "id": 20, "result": {418{ "id": 20, "result": {

404 "data": [419 "data": [

405 { "id": "thr_a", "preview": "Create a TUI", "modelProvider": "openai", "createdAt": 1730831111, "updatedAt": 1730831111 },420 { "id": "thr_a", "preview": "Create a TUI", "ephemeral": false, "modelProvider": "openai", "createdAt": 1730831111, "updatedAt": 1730831111, "name": "TUI prototype", "status": { "type": "notLoaded" } },

406 { "id": "thr_b", "preview": "Fix tests", "modelProvider": "openai", "createdAt": 1730750000, "updatedAt": 1730750000 }421 { "id": "thr_b", "preview": "Fix tests", "ephemeral": true, "modelProvider": "openai", "createdAt": 1730750000, "updatedAt": 1730750000, "status": { "type": "notLoaded" } }

407 ],422 ],

408 "nextCursor": "opaque-token-or-null"423 "nextCursor": "opaque-token-or-null"

409} }424} }

411 426 

412When `nextCursor` is `null`, you have reached the final page.427When `nextCursor` is `null`, you have reached the final page.

413 428 

429### Track thread status changes

430 

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

432 

433```json

434{

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

436 "params": {

437 "threadId": "thr_123",

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

439 }

440}

441```

442 

414### List loaded threads443### List loaded threads

415 444 

416`thread/loaded/list` returns thread IDs currently loaded in memory.445`thread/loaded/list` returns thread IDs currently loaded in memory.

420{ "id": 21, "result": { "data": ["thr_123", "thr_456"] } }449{ "id": 21, "result": { "data": ["thr_123", "thr_456"] } }

421```450```

422 451 

452### Unsubscribe from a loaded thread

453 

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

455 

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

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

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

459 

460If this was the last subscriber, the server unloads the thread and emits a `thread/status/changed` transition to `notLoaded` plus `thread/closed`.

461 

462```json

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

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

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

466 "threadId": "thr_123",

467 "status": { "type": "notLoaded" }

468} }

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

470```

471 

423### Archive a thread472### Archive a thread

424 473 

425Use `thread/archive` to move the persisted thread log (stored as a JSONL file on disk) into the archived sessions directory.474Use `thread/archive` to move the persisted thread log (stored as a JSONL file on disk) into the archived sessions directory.

427```json476```json

428{ "method": "thread/archive", "id": 22, "params": { "threadId": "thr_b" } }477{ "method": "thread/archive", "id": 22, "params": { "threadId": "thr_b" } }

429{ "id": 22, "result": {} }478{ "id": 22, "result": {} }

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

430```480```

431 481 

432Archived threads won't appear in future calls to `thread/list` unless you pass `archived: true`.482Archived threads won't appear in future calls to `thread/list` unless you pass `archived: true`.

437 487 

438```json488```json

439{ "method": "thread/unarchive", "id": 24, "params": { "threadId": "thr_b" } }489{ "method": "thread/unarchive", "id": 24, "params": { "threadId": "thr_b" } }

440{ "id": 24, "result": { "thread": { "id": "thr_b" } } }490{ "id": 24, "result": { "thread": { "id": "thr_b", "name": "Bug bash notes" } } }

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

441```492```

442 493 

443### Trigger thread compaction494### Trigger thread compaction

451{ "id": 25, "result": {} }502{ "id": 25, "result": {} }

452```503```

453 504 

505### Roll back recent turns

506 

507Use `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.

508 

509```json

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

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

512```

513 

454## Turns514## Turns

455 515 

456The `input` field accepts a list of items:516The `input` field accepts a list of items:

480}540}

481```541```

482 542 

543On macOS, `includePlatformDefaults: true` appends a curated platform-default Seatbelt policy for restricted-read sessions. This improves tool compatibility without broadly allowing all of `/System`.

544 

483Examples:545Examples:

484 546 

485```json547```json

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

513 "networkAccess": true575 "networkAccess": true

514 },576 },

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

516 "effort": "medium",578 "effort": "medium",

517 "summary": "concise",579 "summary": "concise",

518 "personality": "friendly",580 "personality": "friendly",

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

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

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

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

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

722 

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

724 

725Use `configRequirements/read` to inspect the effective admin requirements loaded from `requirements.toml` and/or MDM.

726 

727```json

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

729{ "id": 52, "result": {

730 "requirements": {

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

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

733 "featureRequirements": {

734 "personality": true,

735 "unified_exec": false

736 },

737 "network": {

738 "enabled": true,

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

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

741 "dangerouslyAllowAllUnixSockets": false

742 }

743 }

744} }

745```

746 

747`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.

748 

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

750 

751Custom Windows clients can trigger sandbox setup asynchronously instead of blocking on startup checks.

752 

753```json

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

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

756```

757 

758App-server starts setup in the background and later emits a completion notification:

759 

760```json

761{

762 "method": "windowsSandbox/setupCompleted",

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

764}

765```

766 

767Modes:

768 

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

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

658 771 

659## Events772## Events

660 773 

661Event 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.774Event 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.

662 775 

663### Notification opt-out776### Notification opt-out

664 777 

666 779 

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

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

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

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

671 784 

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

676- `fuzzyFileSearch/sessionUpdated` - `{ sessionId, query, files }` with the current matches for the active query.789- `fuzzyFileSearch/sessionUpdated` - `{ sessionId, query, files }` with the current matches for the active query.

677- `fuzzyFileSearch/sessionCompleted` - `{ sessionId }` once indexing and matching for that query completes.790- `fuzzyFileSearch/sessionCompleted` - `{ sessionId }` once indexing and matching for that query completes.

678 791 

792### Windows sandbox setup events

793 

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

795 

679### Turn events796### Turn events

680 797 

681- `turn/started` - `{ turn }` with the turn id, empty `items`, and `status: "inProgress"`.798- `turn/started` - `{ turn }` with the turn id, empty `items`, and `status: "inProgress"`.

691`ThreadItem` is the tagged union carried in turn responses and `item/*` notifications. Common item types include:808`ThreadItem` is the tagged union carried in turn responses and `item/*` notifications. Common item types include:

692 809 

693- `userMessage` - `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).810- `userMessage` - `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).

694- `agentMessage` - `{id, text}` containing the accumulated agent reply.811- `agentMessage` - `{id, text, phase?}` containing the accumulated agent reply. When present, `phase` uses Responses API wire values (`commentary`, `final_answer`).

695- `plan` - `{id, text}` containing proposed plan text in plan mode. Treat the final `plan` item from `item/completed` as authoritative.812- `plan` - `{id, text}` containing proposed plan text in plan mode. Treat the final `plan` item from `item/completed` as authoritative.

696- `reasoning` - `{id, summary, content}` where `summary` holds streamed reasoning summaries and `content` holds raw reasoning blocks.813- `reasoning` - `{id, summary, content}` where `summary` holds streamed reasoning summaries and `content` holds raw reasoning blocks.

697- `commandExecution` - `{id, command, cwd, status, commandActions, aggregatedOutput?, exitCode?, durationMs?}`.814- `commandExecution` - `{id, command, cwd, status, commandActions, aggregatedOutput?, exitCode?, durationMs?}`.

698- `fileChange` - `{id, changes, status}` describing proposed edits; `changes` list `{path, kind, diff}`.815- `fileChange` - `{id, changes, status}` describing proposed edits; `changes` list `{path, kind, diff}`.

699- `mcpToolCall` - `{id, server, tool, status, arguments, result?, error?}`.816- `mcpToolCall` - `{id, server, tool, status, arguments, result?, error?}`.

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

700- `collabToolCall` - `{id, tool, status, senderThreadId, receiverThreadId?, newThreadId?, prompt?, agentStatus?}`.818- `collabToolCall` - `{id, tool, status, senderThreadId, receiverThreadId?, newThreadId?, prompt?, agentStatus?}`.

701- `webSearch` - `{id, query, action?}` for web search requests issued by the agent.819- `webSearch` - `{id, query, action?}` for web search requests issued by the agent.

702- `imageView` - `{id, path}` emitted when the agent invokes the image viewer tool.820- `imageView` - `{id, path}` emitted when the agent invokes the image viewer tool.

753Order of messages:871Order of messages:

754 872 

7551. `item/started` shows the pending `commandExecution` item with `command`, `cwd`, and other fields.8731. `item/started` shows the pending `commandExecution` item with `command`, `cwd`, and other fields.

7562. `item/commandExecution/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, optional `command`, optional `cwd`, optional `commandActions`, and optional `proposedExecpolicyAmendment`.8742. `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.

7573. Client responds with one of the command execution approval decisions above.8753. Client responds with one of the command execution approval decisions above.

7584. `item/completed` returns the final `commandExecution` item with `status: completed | failed | declined`.8764. `serverRequest/resolved` confirms that the pending request has been answered or cleared.

8775. `item/completed` returns the final `commandExecution` item with `status: completed | failed | declined`.

878 

879When `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.

880 

881Codex 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.

759 882 

760### File change approvals883### File change approvals

761 884 

7641. `item/started` emits a `fileChange` item with proposed `changes` and `status: "inProgress"`.8871. `item/started` emits a `fileChange` item with proposed `changes` and `status: "inProgress"`.

7652. `item/fileChange/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, and optional `grantRoot`.8882. `item/fileChange/requestApproval` includes `itemId`, `threadId`, `turnId`, optional `reason`, and optional `grantRoot`.

7663. Client responds with one of the file change approval decisions above.8893. Client responds with one of the file change approval decisions above.

7674. `item/completed` returns the final `fileChange` item with `status: completed | failed | declined`.8904. `serverRequest/resolved` confirms that the pending request has been answered or cleared.

8915. `item/completed` returns the final `fileChange` item with `status: completed | failed | declined`.

892 

893### `tool/requestUserInput`

894 

895When 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.

896 

897### Dynamic tool calls (experimental)

898 

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

900 

901When a dynamic tool is invoked during a turn, app-server emits:

902 

9031. `item/started` with `item.type = "dynamicToolCall"`, `status = "inProgress"`, plus `tool` and `arguments`.

9042. `item/tool/call` as a server request to the client.

9053. The client response payload with returned content items.

9064. `item/completed` with `item.type = "dynamicToolCall"`, the final `status`, and any returned `contentItems` or `success` value.

768 907 

769### MCP tool-call approvals (apps)908### MCP tool-call approvals (apps)

770 909 

771App (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.910App (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.

772 911 

773## Skills912## Skills

774 913 

865 1004 

866## Apps (connectors)1005## Apps (connectors)

867 1006 

868Use `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.1007Use `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.

869 1008 

870```json1009```json

871{ "method": "app/list", "id": 50, "params": {1010{ "method": "app/list", "id": 50, "params": {

881 "name": "Demo App",1020 "name": "Demo App",

882 "description": "Example connector for documentation.",1021 "description": "Example connector for documentation.",

883 "logoUrl": "https://example.com/demo-app.png",1022 "logoUrl": "https://example.com/demo-app.png",

1023 "logoUrlDark": null,

1024 "distributionChannel": null,

1025 "branding": null,

1026 "appMetadata": null,

1027 "labels": null,

884 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",1028 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",

885 "isAccessible": true,1029 "isAccessible": true,

886 "isEnabled": true1030 "isEnabled": true

906 "name": "Demo App",1050 "name": "Demo App",

907 "description": "Example connector for documentation.",1051 "description": "Example connector for documentation.",

908 "logoUrl": "https://example.com/demo-app.png",1052 "logoUrl": "https://example.com/demo-app.png",

1053 "logoUrlDark": null,

1054 "distributionChannel": null,

1055 "branding": null,

1056 "appMetadata": null,

1057 "labels": null,

909 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",1058 "installUrl": "https://chatgpt.com/apps/demo-app/demo-app",

910 "isAccessible": true,1059 "isAccessible": true,

911 "isEnabled": true1060 "isEnabled": true

938}1087}

939```1088```

940 1089 

1090### Config RPC examples for app settings

1091 

1092Use `config/read`, `config/value/write`, and `config/batchWrite` to inspect or update app controls in `config.toml`.

1093 

1094Read the effective app config shape (including `_default` and per-tool overrides):

1095 

1096```json

1097{ "method": "config/read", "id": 60, "params": { "includeLayers": false } }

1098{ "id": 60, "result": {

1099 "config": {

1100 "apps": {

1101 "_default": {

1102 "enabled": true,

1103 "destructive_enabled": true,

1104 "open_world_enabled": true

1105 },

1106 "google_drive": {

1107 "enabled": true,

1108 "destructive_enabled": false,

1109 "default_tools_approval_mode": "prompt",

1110 "tools": {

1111 "files/delete": { "enabled": false, "approval_mode": "approve" }

1112 }

1113 }

1114 }

1115 }

1116} }

1117```

1118 

1119Update a single app setting:

1120 

1121```json

1122{

1123 "method": "config/value/write",

1124 "id": 61,

1125 "params": {

1126 "keyPath": "apps.google_drive.default_tools_approval_mode",

1127 "value": "prompt",

1128 "mergeStrategy": "replace"

1129 }

1130}

1131```

1132 

1133Apply multiple app edits atomically:

1134 

1135```json

1136{

1137 "method": "config/batchWrite",

1138 "id": 62,

1139 "params": {

1140 "edits": [

1141 {

1142 "keyPath": "apps._default.destructive_enabled",

1143 "value": false,

1144 "mergeStrategy": "upsert"

1145 },

1146 {

1147 "keyPath": "apps.google_drive.tools.files/delete.approval_mode",

1148 "value": "approve",

1149 "mergeStrategy": "upsert"

1150 }

1151 ]

1152 }

1153}

1154```

1155 

1156### Detect and import external agent config

1157 

1158Use `externalAgentConfig/detect` to discover migratable external-agent artifacts, then pass the selected entries to `externalAgentConfig/import`.

1159 

1160Detection example:

1161 

1162```json

1163{ "method": "externalAgentConfig/detect", "id": 63, "params": {

1164 "includeHome": true,

1165 "cwds": ["/Users/me/project"]

1166} }

1167{ "id": 63, "result": {

1168 "items": [

1169 {

1170 "itemType": "AGENTS_MD",

1171 "description": "Import /Users/me/project/CLAUDE.md to /Users/me/project/AGENTS.md.",

1172 "cwd": "/Users/me/project"

1173 },

1174 {

1175 "itemType": "SKILLS",

1176 "description": "Copy skill folders from /Users/me/.claude/skills to /Users/me/.agents/skills.",

1177 "cwd": null

1178 }

1179 ]

1180} }

1181```

1182 

1183Import example:

1184 

1185```json

1186{ "method": "externalAgentConfig/import", "id": 64, "params": {

1187 "migrationItems": [

1188 {

1189 "itemType": "AGENTS_MD",

1190 "description": "Import /Users/me/project/CLAUDE.md to /Users/me/project/AGENTS.md.",

1191 "cwd": "/Users/me/project"

1192 }

1193 ]

1194} }

1195{ "id": 64, "result": {} }

1196```

1197 

1198Supported `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.

1199 

941## Auth endpoints1200## Auth endpoints

942 1201 

943The 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.1202The 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.

1# Automations1# Automations

2 2 

3Schedule recurring Codex tasks

4 

5Automate recurring tasks in the background. Codex adds findings to the inbox, or automatically archives the task if there's nothing to report. You can combine automations with [skills](https://developers.openai.com/codex/skills) for more complex tasks.3Automate recurring tasks in the background. Codex adds findings to the inbox, or automatically archives the task if there's nothing to report. You can combine automations with [skills](https://developers.openai.com/codex/skills) for more complex tasks.

6 4 

7Automations run locally in the Codex app. The app needs to be running, and the5Automations run in the background in the Codex app. The app needs to be

8selected project needs to be available on disk.6running, and the selected project needs to be available on disk.

9 7 

10In Git repositories, each automation run starts in a new8In Git repositories, you can choose whether an automation runs in your local

11[worktree](https://developers.openai.com/codex/app/worktrees) so it doesn’t interfere with your main9project or on a new [worktree](https://developers.openai.com/codex/app/worktrees). Both options run in the

12checkout. In non-version-controlled projects, automations run directly in the10background. Worktrees keep automation changes separate from unfinished local

11work, while running in your local project can modify files you are still

12working on. In non-version-controlled projects, automations run directly in the

13project directory.13project directory.

14 14 

15![Automation creation form with schedule and prompt fields](/images/codex/app/create-automation-light.webp) ![Automation creation form with schedule and prompt fields](/images/codex/app/create-automation-dark.webp)15You can also leave the model and reasoning effort on their default settings, or

16choose them explicitly if you want more control over how the automation runs.

16 17 

17![Automation creation form with schedule and prompt fields](/images/codex/app/create-automation-light.webp) ![Automation creation form with schedule and prompt fields](/images/codex/app/create-automation-dark.webp)18![Automation creation form with schedule and prompt fields](/images/codex/app/codex-automations-light.webp)

18 19 

19## Managing tasks20## Managing tasks

20 21 

22 23 

23The "Triage" section acts as your inbox. Automation runs with findings show up there, and you can filter your inbox to show all automation runs or only unread ones.24The "Triage" section acts as your inbox. Automation runs with findings show up there, and you can filter your inbox to show all automation runs or only unread ones.

24 25 

25When an automation runs in a Git repository, Codex uses a dedicated background [worktree](https://developers.openai.com/codex/app/features#worktree-support). In non-version-controlled projects, automations run directly in the project directory. Consider using Git to enable running on background worktrees. You can have the same automation run on multiple projects.26For Git repositories, each automation can run either in your local project or

27on a dedicated background [worktree](https://developers.openai.com/codex/app/features#worktree-support). Use

28worktrees when you want to isolate automation changes from unfinished local

29work. Use local mode when you want the automation to work directly in your main

30checkout, keeping in mind that it can modify files you are actively editing.

31In non-version-controlled projects, automations run directly in the project

32directory. You can have the same automation run on multiple projects.

26 33 

27Automations use your default sandbox settings. In read-only mode, tool calls fail if they require modifying files, network access, or working with apps on your computer. With full access enabled, background automations carry elevated risk. You can adjust sandbox settings in [Settings](https://developers.openai.com/codex/app/settings) and selectively allowlist commands with [rules](https://developers.openai.com/codex/rules).34Automations use your default sandbox settings. In read-only mode, tool calls fail if they require modifying files, network access, or working with apps on your computer. With full access enabled, background automations carry elevated risk. You can adjust sandbox settings in [Settings](https://developers.openai.com/codex/app/settings) and selectively allowlist commands with [rules](https://developers.openai.com/codex/rules).

28 35 

34first. This helps you confirm:41first. This helps you confirm:

35 42 

36- The prompt is clear and scoped correctly.43- The prompt is clear and scoped correctly.

37- The selected model and tools behave as expected.44- The selected or default model, reasoning effort, and tools behave as expected.

38- The resulting diff is reviewable.45- The resulting diff is reviewable.

39 46 

40When you start scheduling runs, review the first few outputs closely and adjust47When you start scheduling runs, review the first few outputs closely and adjust

42 49 

43## Worktree cleanup for automations50## Worktree cleanup for automations

44 51 

45For Git repositories, automations run in worktrees. Frequent schedules can52If you choose worktrees for Git repositories, frequent schedules can create

46create many worktrees over time. Archive automation runs you no longer need,53many worktrees over time. Archive automation runs you no longer need, and avoid

47and avoid pinning runs unless you intend to keep their worktrees.54pinning runs unless you intend to keep their worktrees.

48 55 

49## Permissions and security model56## Permissions and security model

50 57 

66 73 

67If you are in a managed environment, admins can restrict these behaviors using74If you are in a managed environment, admins can restrict these behaviors using

68admin-enforced requirements. For example, they can disallow `approval_policy = "never"` or constrain allowed sandbox modes. See75admin-enforced requirements. For example, they can disallow `approval_policy = "never"` or constrain allowed sandbox modes. See

69[Admin-enforced requirements (`requirements.toml`)](https://developers.openai.com/codex/security#admin-enforced-requirements-requirementstoml).76[Admin-enforced requirements (`requirements.toml`)](https://developers.openai.com/codex/enterprise/managed-configuration#admin-enforced-requirements-requirementstoml).

70 77 

71Automations use `approval_policy = "never"` when your organization policy78Automations use `approval_policy = "never"` when your organization policy

72allows it. If `approval_policy = "never"` is disallowed by admin requirements,79allows it. If `approval_policy = "never"` is disallowed by admin requirements,

174```markdown181```markdown

175Check my commits from the last 24h and submit a $recent-code-bugfix.182Check my commits from the last 24h and submit a $recent-code-bugfix.

176```183```

177 

178[Previous

179 

180Review](https://developers.openai.com/codex/app/review)[Next

181 

182Worktrees](https://developers.openai.com/codex/app/worktrees)

1# Codex app commands1# Codex app commands

2 2 

3Reference for Codex app commands and keyboard shortcuts

4 

5Use these commands and keyboard shortcuts to navigate the Codex app.3Use these commands and keyboard shortcuts to navigate the Codex app.

6 4 

7## Keyboard shortcuts5## Keyboard shortcuts

50| `/review` | Start code review mode to review uncommitted changes or compare against a base branch. |48| `/review` | Start code review mode to review uncommitted changes or compare against a base branch. |

51| `/status` | Show the thread ID, context usage, and rate limits. |49| `/status` | Show the thread ID, context usage, and rate limits. |

52 50 

53## See also51## Deeplinks

54 52 

55- [Features](https://developers.openai.com/codex/app/features)53The Codex app registers the `codex://` URL scheme so links can open specific parts of the app directly.

56- [Settings](https://developers.openai.com/codex/app/settings)54 

55| Deeplink | Opens | Supported query parameters |

56| --- | --- | --- |

57| `codex://settings` | Settings. | None. |

58| `codex://skills` | Skills. | None. |

59| `codex://automations` | Inbox in automation create mode. | None. |

60| `codex://threads/<thread-id>` | A local thread. `<thread-id>` must be a UUID. | None. |

61| `codex://new` | A new thread. | Optional: `prompt`, `originUrl`, `path`. |

62 

63For new-thread deeplinks:

57 64 

58[Previous65- `prompt` prefills the composer.

66- `path` must be an absolute path to a local directory and, when valid, makes that directory the active workspace for the new thread.

67- `originUrl` tries to match one of your current workspace roots by Git remote URL. If both `path` and `originUrl` are present, Codex resolves `path` first.

59 68 

60Local Environments](https://developers.openai.com/codex/app/local-environments)[Next69## See also

61 70 

62Troubleshooting](https://developers.openai.com/codex/app/troubleshooting)71- [Features](https://developers.openai.com/codex/app/features)

72- [Settings](https://developers.openai.com/codex/app/settings)

1# Codex app features1# Codex app features

2 2 

3What you can do with the Codex app

4 

5The Codex app is a focused desktop experience for working on Codex threads in parallel,3The Codex app is a focused desktop experience for working on Codex threads in parallel,

6with built-in worktree support, automations, and Git functionality.4with built-in worktree support, automations, and Git functionality.

7 5 

16session in a specific directory.14session in a specific directory.

17 15 

18If 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

19distinct 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)

20only includes the files for that project.18only includes the files for that project.

21 19 

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

23 

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

25 21 

26## Skills support22## Skills support

27 23 

29IDE Extension. You can also view and explore new skills that your team has25IDE Extension. You can also view and explore new skills that your team has

30created across your different projects by clicking Skills in the sidebar.26created across your different projects by clicking Skills in the sidebar.

31 27 

32![Skills picker showing available skills in the Codex app](/images/codex/app/skill-selector-light.webp) ![Skills picker showing available skills in the Codex app](/images/codex/app/skill-selector-dark.webp)28![Skills picker showing available skills in the Codex app](/images/codex/app/skill-selector-light.webp)

33 

34![Skills picker showing available skills in the Codex app](/images/codex/app/skill-selector-light.webp) ![Skills picker showing available skills in the Codex app](/images/codex/app/skill-selector-dark.webp)

35 29 

36## Automations30## Automations

37 31 

39such as evaluating errors in your telemetry and submitting fixes or creating reports on recent33such as evaluating errors in your telemetry and submitting fixes or creating reports on recent

40codebase changes.34codebase changes.

41 35 

42![Automation creation form with schedule and prompt fields](/images/codex/app/create-automation-light.webp) ![Automation creation form with schedule and prompt fields](/images/codex/app/create-automation-dark.webp)36![Automation creation form with schedule and prompt fields](/images/codex/app/create-automation-light.webp)

43 

44![Automation creation form with schedule and prompt fields](/images/codex/app/create-automation-light.webp) ![Automation creation form with schedule and prompt fields](/images/codex/app/create-automation-dark.webp)

45 37 

46## Modes38## Modes

47 39 

55 47 

56For the full glossary and concepts, explore the [concepts section](https://developers.openai.com/codex/prompting).48For the full glossary and concepts, explore the [concepts section](https://developers.openai.com/codex/prompting).

57 49 

58![New thread composer with Local, Worktree, and Cloud mode options](/images/codex/app/modes-light.webp) ![New thread composer with Local, Worktree, and Cloud mode options](/images/codex/app/modes-dark.webp)50![New thread composer with Local, Worktree, and Cloud mode options](/images/codex/app/modes-light.webp)

59 

60![New thread composer with Local, Worktree, and Cloud mode options](/images/codex/app/modes-light.webp) ![New thread composer with Local, Worktree, and Cloud mode options](/images/codex/app/modes-dark.webp)

61 51 

62## Built-in Git tools52## Built-in Git tools

63 53 

71 61 

72For more advanced Git tasks, use the [integrated terminal](#integrated-terminal).62For more advanced Git tasks, use the [integrated terminal](#integrated-terminal).

73 63 

74![Git diff and commit panel with a commit message field](/images/codex/app/git-commit-light.webp) ![Git diff and commit panel with a commit message field](/images/codex/app/git-commit-dark.webp)64![Git diff and commit panel with a commit message field](/images/codex/app/git-commit-light.webp)

75 

76![Git diff and commit panel with a commit message field](/images/codex/app/git-commit-light.webp) ![Git diff and commit panel with a commit message field](/images/codex/app/git-commit-dark.webp)

77 65 

78## Worktree support66## Worktree support

79 67 

88 76 

89[Learn more about using worktrees in the Codex app.](https://developers.openai.com/codex/app/worktrees)77[Learn more about using worktrees in the Codex app.](https://developers.openai.com/codex/app/worktrees)

90 78 

91![Worktree thread view showing branch actions and worktree details](/images/codex/app/worktree-light.webp) ![Worktree thread view showing branch actions and worktree details](/images/codex/app/worktree-dark.webp)79![Worktree thread view showing branch actions and worktree details](/images/codex/app/worktree-light.webp)

92 

93![Worktree thread view showing branch actions and worktree details](/images/codex/app/worktree-light.webp) ![Worktree thread view showing branch actions and worktree details](/images/codex/app/worktree-dark.webp)

94 80 

95## Integrated terminal81## Integrated terminal

96 82 

99pressing <kbd>Cmd</kbd>+<kbd>J</kbd>.85pressing <kbd>Cmd</kbd>+<kbd>J</kbd>.

100 86 

101Use the terminal to validate changes, run scripts, and perform Git operations87Use the terminal to validate changes, run scripts, and perform Git operations

102without leaving the app.88without leaving the app. Codex can also read the current terminal output, so

89it can check the status of a running development server or refer back to a

90failed build while it works with you.

103 91 

104Common tasks include:92Common tasks include:

105 93 

113Note that <kbd>Cmd</kbd>+<kbd>K</kbd> opens the command palette in the Codex101Note that <kbd>Cmd</kbd>+<kbd>K</kbd> opens the command palette in the Codex

114app. It doesn't clear the terminal. To clear the terminal use <kbd>Ctrl</kbd>+<kbd>L</kbd>.102app. It doesn't clear the terminal. To clear the terminal use <kbd>Ctrl</kbd>+<kbd>L</kbd>.

115 103 

116![Integrated terminal drawer open beneath a Codex thread](/images/codex/app/integrated-terminal-light.webp) ![Integrated terminal drawer open beneath a Codex thread](/images/codex/app/integrated-terminal-dark.webp)104![Integrated terminal drawer open beneath a Codex thread](/images/codex/app/integrated-terminal-light.webp)

105 

106## Native Windows sandbox

117 107 

118![Integrated terminal drawer open beneath a Codex thread](/images/codex/app/integrated-terminal-light.webp) ![Integrated terminal drawer open beneath a Codex thread](/images/codex/app/integrated-terminal-dark.webp)108On Windows, Codex can run natively in PowerShell with a native Windows sandbox

109instead of requiring WSL or a virtual machine. This lets you stay in

110Windows-native workflows while keeping bounded permissions in place.

111 

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

113 

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

119 115 

120## Voice dictation116## Voice dictation

121 117 

122Use 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.118Use 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.

123 119 

124![Voice dictation indicator in the composer with a transcribed prompt](/images/codex/app/voice-dictation-light.webp) ![Voice dictation indicator in the composer with a transcribed prompt](/images/codex/app/voice-dictation-dark.webp)120![Voice dictation indicator in the composer with a transcribed prompt](/images/codex/app/voice-dictation-light.webp)

125 

126![Voice dictation indicator in the composer with a transcribed prompt](/images/codex/app/voice-dictation-light.webp) ![Voice dictation indicator in the composer with a transcribed prompt](/images/codex/app/voice-dictation-dark.webp)

127 121 

128## Floating pop-out window122## Floating pop-out window

129 123 

134You can also toggle the pop-out window to stay on top when you want it to remain128You can also toggle the pop-out window to stay on top when you want it to remain

135visible across your workflow.129visible across your workflow.

136 130 

137![Pop-out window preview in light mode](/images/codex/app/popover-light.webp) ![Pop-out window preview in light mode](/images/codex/app/popover-dark.webp)131![Pop-out window preview in light mode](/images/codex/app/popover-light.webp)

138 

139![Pop-out window preview in light mode](/images/codex/app/popover-light.webp) ![Pop-out window preview in light mode](/images/codex/app/popover-dark.webp)

140 132 

141---133---

142 134 

172opening separate projects or using worktrees rather than asking Codex to roam164opening separate projects or using worktrees rather than asking Codex to roam

173outside the project root.165outside the project root.

174 166 

175For details on how Codex handles sandboxing, check out the [security documentation](https://developers.openai.com/codex/security).167For a high-level overview, see [Sandboxing](https://developers.openai.com/codex/concepts/sandboxing). For

168configuration details, see the

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

176 170 

177## MCP support171## MCP support

178 172 

185 179 

186Codex ships with a first-party web search tool. For local tasks in the Codex IDE Extension, Codex180Codex ships with a first-party web search tool. For local tasks in the Codex IDE Extension, Codex

187enables web search by default and serves results from a web search cache. If you configure your181enables web search by default and serves results from a web search cache. If you configure your

188sandbox for [full access](https://developers.openai.com/codex/security), web search defaults to live results. See182sandbox for [full access](https://developers.openai.com/codex/agent-approvals-security), web search defaults to live results. See

189[Config basics](https://developers.openai.com/codex/config-basic) to disable web search or switch to live results that fetch the183[Config basics](https://developers.openai.com/codex/config-basic) to disable web search or switch to live results that fetch the

190most recent data.184most recent data.

191 185 

216- [Automations](https://developers.openai.com/codex/app/automations)210- [Automations](https://developers.openai.com/codex/app/automations)

217- [Local environments](https://developers.openai.com/codex/app/local-environments)211- [Local environments](https://developers.openai.com/codex/app/local-environments)

218- [Worktrees](https://developers.openai.com/codex/app/worktrees)212- [Worktrees](https://developers.openai.com/codex/app/worktrees)

219 

220[Previous

221 

222Overview](https://developers.openai.com/codex/app)[Next

223 

224Settings](https://developers.openai.com/codex/app/settings)

1# Local environments1# Local environments

2 2 

3Configure common actions and setup scripts for worktrees

4 

5Local environments let you configure setup steps for worktrees as well as common actions for a project.3Local environments let you configure setup steps for worktrees as well as common actions for a project.

6 4 

7You configure your local environments through the [Codex app settings](codex://settings) pane. You can check the generated file into your project's Git repository to share with others.5You configure your local environments through the [Codex app settings](codex://settings) pane. You can check the generated file into your project's Git repository to share with others.

31 29 

32Actions are helpful to keep you from typing common actions like triggering a build for your project or starting a development server. For one-off quick debugging you can use the integrated terminal directly.30Actions are helpful to keep you from typing common actions like triggering a build for your project or starting a development server. For one-off quick debugging you can use the integrated terminal directly.

33 31 

34![Project actions list shown in Codex app settings](/images/codex/app/actions-light.webp) ![Project actions list shown in Codex app settings](/images/codex/app/actions-dark.webp)32![Project actions list shown in Codex app settings](/images/codex/app/actions-light.webp)

35 

36![Project actions list shown in Codex app settings](/images/codex/app/actions-light.webp) ![Project actions list shown in Codex app settings](/images/codex/app/actions-dark.webp)

37 33 

38For example, for a Node.js project you might create a "Run" action that contains the following script:34For example, for a Node.js project you might create a "Run" action that contains the following script:

39 35 

44If the commands for your action are platform-specific, define platform-specific scripts for macOS, Windows, and Linux.40If the commands for your action are platform-specific, define platform-specific scripts for macOS, Windows, and Linux.

45 41 

46To identify your actions, choose an icon associated with each action.42To identify your actions, choose an icon associated with each action.

47 

48[Previous

49 

50Worktrees](https://developers.openai.com/codex/app/worktrees)[Next

51 

52Commands](https://developers.openai.com/codex/app/commands)

1# Review1# Review

2 2 

3Review and iterate with Codex on changes inside the app

4 

5The review pane helps you understand what Codex changed, give targeted feedback, and decide what to keep.3The review pane helps you understand what Codex changed, give targeted feedback, and decide what to keep.

6 4 

7It only works for projects that live inside a Git repository. If your project5It only works for projects that live inside a Git repository. If your project

57If you use `/review` to run a code review, comments will show up directly55If you use `/review` to run a code review, comments will show up directly

58inline in the review pane.56inline in the review pane.

59 57 

60![Inline code review comments displayed in the review pane](/images/codex/app/inline-code-review-light.webp) ![Inline code review comments displayed in the review pane](/images/codex/app/inline-code-review-dark.webp)58![Inline code review comments displayed in the review pane](/images/codex/app/inline-code-review-light.webp)

61 

62![Inline code review comments displayed in the review pane](/images/codex/app/inline-code-review-light.webp) ![Inline code review comments displayed in the review pane](/images/codex/app/inline-code-review-dark.webp)

63 59 

64## Staging and reverting files60## Staging and reverting files

65 61 

81Git can represent both staged and unstaged changes in the same file. When that77Git can represent both staged and unstaged changes in the same file. When that

82happens, it can look like the pane is showing “the same file twice” across78happens, it can look like the pane is showing “the same file twice” across

83staged and unstaged views. That's normal Git behavior.79staged and unstaged views. That's normal Git behavior.

84 

85[Previous

86 

87Settings](https://developers.openai.com/codex/app/settings)[Next

88 

89Automations](https://developers.openai.com/codex/app/automations)

1# Codex app settings1# Codex app settings

2 2 

3Configure Codex app behavior and preferences

4 

5Use the settings panel to tune how the Codex app behaves, how it opens files,3Use the settings panel to tune how the Codex app behaves, how it opens files,

6and how it connects to tools. Open [**Settings**](codex://settings) from the app menu or4and how it connects to tools. Open [**Settings**](codex://settings) from the app menu or

7press <kbd>Cmd</kbd>+<kbd>,</kbd>.5press <kbd>Cmd</kbd>+<kbd>,</kbd>.

12require <kbd>Cmd</kbd>+<kbd>Enter</kbd> for multiline prompts or prevent sleep while a10require <kbd>Cmd</kbd>+<kbd>Enter</kbd> for multiline prompts or prevent sleep while a

13thread runs.11thread runs.

14 12 

15## Appearance

16 

17Pick a theme, decide whether the window is solid, and adjust UI or code fonts. Font

18choices apply across the app, including the diff review panel and terminal.

19 

20## Notifications13## Notifications

21 14 

22Choose when turn completion notifications appear, and whether the app should prompt for15Choose when turn completion notifications appear, and whether the app should prompt for

26 19 

27Codex agents in the app inherit the same configuration as the IDE and CLI extension.20Codex agents in the app inherit the same configuration as the IDE and CLI extension.

28Use the in-app controls for common settings, or edit `config.toml` for advanced21Use the in-app controls for common settings, or edit `config.toml` for advanced

29options. See [Codex security](https://developers.openai.com/codex/security) and22options. See [Codex security](https://developers.openai.com/codex/agent-approvals-security) and

30[config basics](https://developers.openai.com/codex/config-basic) for more detail.23[config basics](https://developers.openai.com/codex/config-basic) for more detail.

31 24 

25## Appearance

26 

27In **Settings**, you can change the Codex app appearance by choosing a base theme,

28adjusting accent, background, and foreground colors, and changing the UI and code

29fonts. You can also share your custom theme with friends.

30 

31![Codex app Appearance settings showing theme selection, color controls, and font options](/images/codex/app/theme-selection-light.webp)

32 

32## Git33## Git

33 34 

34Use Git settings to standardize branch naming and choose whether Codex uses force35Use Git settings to standardize branch naming and choose whether Codex uses force

54 55 

55The **Archived threads** section lists archived chats with dates and project56The **Archived threads** section lists archived chats with dates and project

56context. Use **Unarchive** to restore a thread.57context. Use **Unarchive** to restore a thread.

57 

58[Previous

59 

60Features](https://developers.openai.com/codex/app/features)[Next

61 

62Review](https://developers.openai.com/codex/app/review)

1# Troubleshooting1# Troubleshooting

2 2 

3FAQ and fixes for common Codex app issues

4 

5## Frequently Asked Questions3## Frequently Asked Questions

6 4 

7### Files appear in the side panel that Codex didn't edit5### Files appear in the side panel that Codex didn't edit

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

35 33 

36The 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

37you’re missing threads, check whether you have any filters applied by clicking35you're missing threads, click the filter icon next to the **Threads** label and

38the 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.

39 39 

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

41 41 

134**Fonts aren't rendering correctly**134**Fonts aren't rendering correctly**

135 135 

136Codex uses the same font for the review pane, integrated terminal and any other code displayed inside the app. You can configure the font inside the [Settings](codex://settings) pane as **Code font**.136Codex uses the same font for the review pane, integrated terminal and any other code displayed inside the app. You can configure the font inside the [Settings](codex://settings) pane as **Code font**.

137 

138[Previous

139 

140Commands](https://developers.openai.com/codex/app/commands)

1# Windows

2 

3The [Codex app for Windows](https://get.microsoft.com/installer/download/9PLM9XGG6VKS?cid=website_cta_psi) gives you one interface for

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

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).

8 

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

10 

11## Download and update the Codex app

12 

13Download the Codex app from the

14[Microsoft Store](https://get.microsoft.com/installer/download/9PLM9XGG6VKS?cid=website_cta_psi).

15 

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

17 

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

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

20 

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

22distribution through enterprise management tools.

23 

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

25the Microsoft Store UI, run:

26 

27```powershell

28winget install Codex -s msstore

29```

30 

31## Native sandbox

32 

33The Codex app on Windows supports a native [Windows sandbox](https://developers.openai.com/codex/windows#windows-sandbox) when the agent runs in PowerShell, and uses Linux sandboxing when you run the agent in [Windows Subsystem for Linux (WSL)](#windows-subsystem-for-linux-wsl). To apply sandbox protections in either mode, set sandbox permissions to **Default permissions** in the Composer before sending messages to Codex.

34 

35Running Codex in full access mode means Codex is not limited to your project

36 directory and might perform unintentional destructive actions that can lead to

37 data loss. Keep sandbox boundaries in place and use [rules](https://developers.openai.com/codex/rules) for

38 targeted exceptions, or set your [approval policy to

39 never](https://developers.openai.com/codex/agent-approvals-security#run-without-approval-prompts) to have

40 Codex attempt to solve problems without asking for escalated permissions,

41 based on your [approval and security setup](https://developers.openai.com/codex/agent-approvals-security).

42 

43## Customize for your dev setup

44 

45### Preferred editor

46 

47Choose a default app for **Open**, such as Visual Studio, VS Code, or another

48editor. You can override that choice per project. If you already picked a

49different app from the **Open** menu for a project, that project-specific

50choice takes precedence.

51 

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

53 

54### Integrated terminal

55 

56You can also choose the default integrated terminal. Depending on what you have

57installed, options include:

58 

59- PowerShell

60- Command Prompt

61- Git Bash

62- WSL

63 

64This change applies only to new terminal sessions. If you already have an

65integrated terminal open, restart the app or start a new thread before

66expecting the new default terminal to appear.

67 

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

69 

70## Windows Subsystem for Linux (WSL)

71 

72By default, the Codex app uses the Windows-native agent. That means the agent

73runs commands in PowerShell. The app can still work with projects that live in

74Windows Subsystem for Linux (WSL) by using the `wsl` CLI when needed.

75 

76If you want to add a project from the WSL filesystem, click **Add new project**

77or press <kbd>Ctrl</kbd>+<kbd>O</kbd>, then type `\\wsl$\` into the File

78Explorer window. From there, choose your Linux distribution and the folder you

79want to open.

80 

81If you plan to keep using the Windows-native agent, prefer storing projects on

82your Windows filesystem and accessing them from WSL through

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

84directly from the WSL filesystem.

85 

86If you want the agent itself to run in WSL, open **[Settings](codex://settings)**,

87switch the agent from Windows native to WSL, and **restart the app**. The

88change doesn't take effect until you restart. Your projects should remain in

89place after restart.

90 

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

92 

93You configure the integrated terminal independently from the agent. See

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

95terminal options. You can keep the agent in WSL and still use PowerShell in the

96terminal, or use WSL for both, depending on your workflow.

97 

98## Useful developer tools

99 

100Codex works best when a few common developer tools are already installed:

101 

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

103 revert changes.

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

105 efficiently.

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

107 efficiently.

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

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

110 

111Install them with the default Windows package manager `winget` by pasting this

112into the [integrated terminal](https://developers.openai.com/codex/app/features#integrated-terminal) or

113asking Codex to install them:

114 

115```powershell

116winget install --id Git.Git

117winget install --id OpenJS.NodeJS.LTS

118winget install --id Python.Python.3.14

119winget install --id Microsoft.DotNet.SDK.10

120winget install --id GitHub.cli

121```

122 

123After installing GitHub CLI, run `gh auth login` to enable GitHub features in

124the app.

125 

126If you need a different Python or .NET version, change the package IDs to the

127version you want.

128 

129## Troubleshooting and FAQ

130 

131### Run commands with elevated permissions

132 

133If you need Codex to run commands with elevated permissions, start the Codex app

134itself as an administrator. After installation, open the Start menu, find

135Codex, and choose Run as administrator. The Codex agent inherits that

136permission level.

137 

138### PowerShell execution policy blocks commands

139 

140If you have never used tools such as Node.js or `npm` in PowerShell before, the

141Codex agent or integrated terminal may hit execution policy errors.

142 

143This can also happen if Codex creates PowerShell scripts for you. In that case,

144you may need a less restrictive execution policy before PowerShell will run

145them.

146 

147An error may look something like this:

148 

149```text

150npm.ps1 cannot be loaded because running scripts is disabled on this system.

151```

152 

153A common fix is to set the execution policy to `RemoteSigned`:

154 

155```powershell

156Set-ExecutionPolicy -ExecutionPolicy RemoteSigned

157```

158 

159For details and other options, check Microsoft's

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

161before changing the policy.

162 

163### Local environment scripts on Windows

164 

165If your [local environment](https://developers.openai.com/codex/app/local-environments) uses cross-platform

166commands such as `npm` scripts, you can keep one shared setup script or

167set of actions for every platform.

168 

169If you need Windows-specific behavior, create Windows-specific setup scripts or

170Windows-specific actions.

171 

172Actions run in the environment used by your integrated terminal. See

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

174 

175Local setup scripts run in the agent environment: WSL if the agent uses WSL,