claude-code-20261106T040701Z / documentation capture

agent-sdk/python Changed · +5 / -12 lines

from line 3664

36643664

36653665### `SandboxIgnoreViolations`

36663666

3667Configuration for ignoring specific sandbox violations.

3667Violations to leave out of the sandbox's violation report. Each key matches part of a command, or `*` for every command, and each value lists text to match in a violation line: `{"*": ["/etc/hosts"]}` hides violations that mention `/etc/hosts`. A matching access is still blocked. See [`sandbox.ignoreViolations`](https://code.claude.com/docs/en/settings-reference#sandbox-ignoreviolations).

36683668

36693669```python theme={null}

3670class SandboxIgnoreViolations(TypedDict, total=False):

3671 file: list[str]

3672 network: list[str]

3670SandboxIgnoreViolations = dict[str, list[str]]

36733671```

3674

3676| :- | :- | :- | :- |

36793672

36803673### Permissions Fallback for Unsandboxed Commands

36813674

agent-sdk/typescript Changed · +20 / -8 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 1927

19271927

19281928The same pair of fields appears on [`SDKSystemMessage`](#sdksystemmessage) and on the [`SDKControlInitializeResponse`](#sdkcontrolinitializeresponse), so you can read the fast mode state before the first turn.

19291929

1930The `origin` field forwards the [`SDKMessageOrigin`](#sdkmessageorigin) of the user message that triggered this result. Results that carry `origin: { kind: "task-notification" }` include:

1930The `origin` field holds the [`SDKMessageOrigin`](#sdkmessageorigin) that Claude Code assigned to the user message that triggered this result, not a copy of the `origin` you sent. Results that carry `origin: { kind: "task-notification" }` include:

19311931

19321932* **Synthetic follow-up turns**: when the SDK injects a synthetic follow-up turn, such as for a finished background task, the resulting `SDKResultMessage` carries this kind

19331933* **Fired scheduled tasks and messages from other sessions**: cloud scheduled tasks whose trigger fired and server-verified messages from your other sessions arrive with this kind too, each with the `subkind` described in [Task-notification subkinds](#task-notification-subkinds)

from line 1936

19361936

19371937When several background-task completions are queued together, Claude Code can answer them in one turn rather than one turn each. Each completion still produces its own result with this origin. All but the last of the completions Claude Code answers together produce empty results with `num_turns: 0`, in order, and the last one's result carries the turn that answers them all.

19381938

1939The field is absent for results emitted before any user turn, such as startup errors.

1939`origin` is absent when Claude Code assigned none, such as:

19401940

1941* On a turn you start with a message that has neither `origin` nor [`isSynthetic`](#sdkusermessage)

1942* On results emitted before any user turn, such as startup errors

1943

19411944When a `PreToolUse` hook returns `permissionDecision: "defer"`, the result has `stop_reason: "tool_deferred"` and `deferred_tool_use` carries the pending tool's `id`, `name`, and `input`. Read this field to surface the request in your own UI, then resume with the same `session_id` to continue. See [Defer a tool call for later](https://code.claude.com/docs/en/hooks.md#defer-a-tool-call-for-later) for the full round trip.

19421945

19431946#### `user_message_uuid`

from line 2434

24312434

24322435### `SDKMessageOrigin`

24332436

2434Provenance of a user-role message. This appears as `origin` on [`SDKUserMessage`](#sdkusermessage) and is forwarded onto the corresponding [`SDKResultMessage`](#sdkresultmessage) so you can tell what triggered a given turn.

2437Provenance of a user-role message. This appears as `origin` on [`SDKUserMessage`](#sdkusermessage). The [`SDKResultMessage`](#sdkresultmessage) for a turn carries the `origin` that Claude Code assigned, so you can tell what triggered that turn.

24352438

24362439```typescript theme={null}

24372440type SDKMessageOrigin =

from line 2461

24582461 | { kind: "unclassified" };

24592462```

24602463

2464Your application can set these kinds of `origin` on a message it sends:

2465

2466* `{ kind: "human" }`: what the user typed

2467* `{ kind: "task-notification", subkind: "scheduled-trigger" }`: a [scheduled run you declare](#declare-a-scheduled-run)

2468

2469Leave the other kinds to Claude Code and Anthropic servers. If you set one of those kinds, Claude reads the message as the user's by default.

2470

2471To send text the user didn't write, such as a fetched page or another agent's output, send it as its own message with [`isSynthetic`](#sdkusermessage) set to `true` and `origin` unset. Also set [`client_composed`](#sdkusermessage) to `true`, so that text starting with `/` doesn't run as a command.

2472

24612473| `kind` | Meaning |

24622474| - | - |

2463| `human` | Direct input from the end user. If your application forwards what the user typed as a user message, set its `origin` to `{ kind: "human" }` explicitly: Claude Code treats a user message with no `origin` as unattributed, and checks that require a human-typed prompt, such as the [`ultracode` workflow keyword](https://code.claude.com/docs/en/workflows#ask-for-a-workflow-in-your-prompt), don't accept it. Before v2.1.210, Claude Code treated an absent `origin` on a user message as human input. |

2475| `human` | Direct input from the end user. If your application forwards what the user typed as a user message, set its `origin` to `{ kind: "human" }`. Without that `origin`, Claude still reads the message as the user's, but checks that require a human-typed prompt, such as the [`ultracode` workflow keyword](https://code.claude.com/docs/en/workflows#ask-for-a-workflow-in-your-prompt), don't accept the message. |

24642476| `channel` | Message arriving on a [channel](https://code.claude.com/docs/en/channels.md). `server` is the source MCP server name. |

2465| `peer` | Message from another agent: an in-process [teammate](https://code.claude.com/docs/en/agent-teams.md) or a [cross-session peer](https://code.claude.com/docs/en/cross-session-messaging.md), another of your Claude Code sessions. See [Peer origin fields](#peer-origin-fields) for the per-field semantics and the trust model. |

2477| `peer` | Message from another Claude Code agent: an in-process [teammate](https://code.claude.com/docs/en/agent-teams.md) or a [cross-session peer](https://code.claude.com/docs/en/cross-session-messaging.md), another of your Claude Code sessions. The [desktop app](https://code.claude.com/docs/en/desktop.md#work-across-sessions), which relays such messages between your sessions, declares this kind with [`fromMode`](#peer-origin-fields). To relay another agent's output from your own application, set `isSynthetic` and `client_composed` instead. See [Peer origin fields](#peer-origin-fields) for the per-field semantics and the trust model. |

24662478| `task-notification` | Synthetic turn injected for a delivery that arrives without a fresh user prompt, such as a finished background task; see [`SDKTaskNotificationMessage`](#sdktasknotificationmessage) for that arm. A prompt your application [declares as a scheduled run](#declare-a-scheduled-run) carries this kind too. The optional `subkind` marks what raised the notification. See [Task-notification subkinds](#task-notification-subkinds). |

24672479| `coordinator` | Message from a team coordinator in an [agent team](https://code.claude.com/docs/en/agent-teams.md). |

24682480| `auto-continuation` | Synthetic turn injected when the session continues without fresh user input, such as a command result that triggers a follow-up prompt. |

2469| `unclassified` | Injected turn whose origin couldn't be determined. Requires Claude Code v2.1.223 or later. When Claude Code receives an [`SDKUserMessage`](#sdkusermessage) with `isSynthetic: true` and can't classify it as any other `kind`, it sets this kind as the message arrives and frames the turn to the model as a non-user source rather than treating it as human input. Your application shouldn't set this value. |

2481| `unclassified` | Message marked as not coming from the user, such as an [`SDKUserMessage`](#sdkusermessage) you send with `isSynthetic: true`. Requires Claude Code v2.1.223 or later. |

24702482

24712483### Task-notification subkinds

24722484

from line 2502

24902502A `peer` origin identifies which agent sent the message: an in-process [teammate](https://code.claude.com/docs/en/agent-teams.md) sending to `main` with `SendMessage`, or a [cross-session peer](https://code.claude.com/docs/en/cross-session-messaging.md), another of your Claude Code sessions. Cross-session peers require Claude Code v2.1.224 or later on macOS and Linux; see [cross-session messaging availability](https://code.claude.com/docs/en/cross-session-messaging.md#availability) for the native Windows requirement. A cross-session peer can run on the same machine, or on [another of your machines](https://code.claude.com/docs/en/cross-session-messaging.md#message-sessions-on-other-machines) when its message arrives through [Remote Control](https://code.claude.com/docs/en/remote-control.md).

24912503

24922504* `from`: the teammate's name, or the sender address for a cross-session peer. For a [one-way cross-machine message](https://code.claude.com/docs/en/cross-session-messaging.md#message-sessions-on-other-machines), the sender has no reply address and `from` is `"unknown"`. The value is sender-authored; `verifiedPeerPid` is the verified identity.

2493* `fromMode`: the sending session's permission class, `bypass` or `prompting`, declared by a host that relays a peer message between your sessions, such as the [desktop app](https://code.claude.com/docs/en/desktop.md#work-across-sessions). Claude Code reads it in the receiving session when it applies the [inbound controls](https://code.claude.com/docs/en/cross-session-messaging.md#control-inbound-messages). Requires Agent SDK v0.3.234 or later.

2505* `fromMode`: the sending session's permission class, `bypass` or `prompting`. Claude Code reads it in the receiving session when it applies the [inbound controls](https://code.claude.com/docs/en/cross-session-messaging.md#control-inbound-messages). Requires Agent SDK v0.3.234 or later.

24942506* `senderTaskId`: the teammate's task ID. Absent for a cross-session peer.

24952507* `name`: the sender's display name, normalized by Claude Code: it strips Unicode control, format, surrogate, and line or paragraph separator code points, then trims the result and caps it at 64 code points with an ellipsis. Requires Claude Code v2.1.205 or later.

24962508* `body`: the decoded message body with the peer envelope stripped, byte-exact with what the model sees. Present for a single teammate message, absent when several are merged; for a cross-session peer, present only when the turn is exactly one peer envelope formed by Claude Code. Render `name` and `body` instead of re-parsing the message text. Before v2.1.299, merged messages kept the first message's `body`. Requires Claude Code v2.1.205 or later.

from line 4773

47614773

47624774Returns the scheduled cron jobs: durable jobs from `.claude/scheduled_tasks.json` and session-only jobs from the current session. A session-only job carries `durable: false`; jobs read from disk omit the field.

47634775

4764`nextFireAt` is the job's next run time in epoch milliseconds, [jitter](https://code.claude.com/docs/en/scheduled-tasks.md#jitter) included. No value is earlier than the `CronList` call: a job whose time [passed without a run](https://code.claude.com/docs/en/scheduled-tasks.md#how-scheduled-tasks-run) carries the call's time. The field requires TypeScript Agent SDK v0.3.299 or later and Claude Code v2.1.299 or later.

4765

4766### ScheduleWakeup

4767

4768**Tool name:** `ScheduleWakeup`

4769

4770```typescript theme={null}

4771type ScheduleWakeupOutput = {

4772 scheduledFor: number;

4773 clampedDelaySeconds: number;

4774 wasClamped: boolean;

4775 stopped?: boolean;

4776 cancelledWakeups?: number;

4777};

4778```

4779

4780Returns when the wake-up will fire as an epoch millisecond timestamp, the delay actually used, and whether the requested delay was clamped. The `stopped` field is `true` when the call ended the loop with `stop: true`. It requires Claude Code v2.1.202 or later. The `cancelledW

4776`nextFireAt` is the job's next run time in epoch milliseconds, [jitter](https://code.claude.com/docs/en/scheduled-tasks.md#jitter) included. No value is earlier than the `CronList` call: a job whose time [passed with

fast-mode Changed · +6 / -6 lines

from line 31

3131In the CLI, toggle fast mode in either of these ways:

3232

3333* Run `/fast`, press Space to toggle on or off, then press Enter to confirm

34* Set `"fastMode": true` in your [user settings file](https://code.claude.com/docs/en/settings.md)

34* On a model that supports fast mode, set `"fastMode": true` in your [user settings file](https://code.claude.com/docs/en/settings.md). If you set it on any other model, you stay on that model with fast mode off.

3535

36By default, fast mode you turn on in an interactive session persists across sessions. You can configure fast mode to reset each session. See [require per-session opt-in](#require-per-session-opt-in) for details.

36By default, fast mode you turn on in an interactive session persists across sessions on a supported model. You can configure fast mode to reset each session. See [require per-session opt-in](#require-per-session-opt-in) for details.

3737

3838Outside a [cloud session](#use-fast-mode-in-cloud-sessions), in [non-interactive mode](https://code.claude.com/docs/en/headless.md) with the `-p` flag, `/fast` works only in a session launched with fast mode in its [`--settings`](https://code.claude.com/docs/en/cli-reference#cli-flags) value, for example `claude -p --settings '{"fastMode": true}'`; the toggle then applies to that session only and isn't saved as your default. The `-p` form requires Claude Code v2.1.205 or later. Elsewhere in non-interactive mode, the command reports that fast mode isn't available.

3939

from line 41

4141

4242For the best cost efficiency, enable fast mode at the start of a session rather than switching mid-conversation. See [understand the cost tradeoff](#understand-the-cost-tradeoff) for details.

4343

44When you enable fast mode:

44When you enable fast mode with `/fast`:

4545

4646* If your current model doesn't support fast mode, Claude Code switches to Opus

4747* You'll see a confirmation message: "Fast mode ON"

from line 192

192192

193193### Require per-session opt-in

194194

195By default, fast mode a user turns on in an interactive session persists across sessions. To change this, set `fastModePerSessionOptIn` to `true` in any [settings file](https://code.claude.com/docs/en/settings.md#where-settings-live), which causes each session to start with fast mode off and requires users to explicitly enable it with `/fast`. Owners on [Team](https://claude.com/pricing?utm_source=claude_code\&utm_medium=docs\&utm_content=fast_mode_teams#team-&-enterprise) or [Enterprise](https://anthropic.com/contact-sales?utm_source=claude_code\&utm_medium=docs\&utm_content=fast_mode_enterprise) plans can deploy it organization-wide through [server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md).

195By default, fast mode a user turns on in an interactive session persists across sessions on a supported model. To change this, set `fastModePerSessionOptIn` to `true` in any [settings file](https://code.claude.com/docs/en/settings.md#where-settings-live), which causes each session to start with fast mode off and requires users to explicitly enable it with `/fast`. Owners on [Team](https://claude.com/pricing?utm_source=claude_code\&utm_medium=docs\&utm_content=fast_mode_teams#team-&-enterprise) or [Enterprise](https://anthropic.com/contact-sales?utm_source=claude_code\&utm_medium=docs\&utm_content=fast_mode_enterprise) plans can deploy it organization-wide through [server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md).

196196

197197```json theme={null}

198198{

from line 217

217217

218218If you run out of usage credits mid-session, Claude Code retries each rejected fast mode request at standard speed and pricing, so you keep working, and there is no cooldown. How you see the rejection depends on the session type:

219219

220* In an interactive session, Claude Code shows a "Fast mode disabled · usage credits exhausted" notification and turns fast mode off for the rest of the session. Your saved fast mode preference doesn't change; run `/fast` to turn fast mode back on.

220* In an interactive session, Claude Code shows a "Fast mode disabled · Out of usage credits" notification and turns fast mode off. Your saved fast mode preference doesn't change; run `/fast` to turn fast mode back on.

221221* In [non-interactive mode](https://code.claude.com/docs/en/headless.md) with `--output-format stream-json`, and through the Agent SDK, Claude Code emits the same text on the message stream as a `system` message with subtype `notification`, once per turn while you're out of usage credits. Fast mode stays on. Requires Claude Code v2.1.221 or later.

222222

223223## Research preview

hooks Changed · +3 / -2 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 290

290290| `SessionStart` | how the session started | `startup`, `resume`, `clear`, `compact`, `fork` |

291291| `Setup` | which CLI flag triggered setup | `init`, `maintenance` |

292292| `SessionEnd` | why the session ended | `clear`, `resume`, `logout`, `prompt_input_exit`, `other` |

293| `Notification` | notification type | `permission_prompt`, `idle_prompt`, `auth_success`, `elicitation_dialog`, `elicitation_url_dialog`, `elicitation_complete`, `elicitation_response`, `agent_needs_input`, `agent_completed`, `quota_auto_resume_fired`, `quota_auto_resume_stale`, `quota_auto_resume_disabled`, `plugin_notification` |

293| `Notification` | notification type | `permission_prompt`, `idle_prompt`, `auth_success`, `auth_storage_failure`, `elicitation_dialog`, `elicitation_url_dialog`, `elicitation_complete`, `elicitation_response`, `agent_needs_input`, `agent_completed`, `quota_auto_resume_fired`, `quota_auto_resume_stale`, `quota_auto_resume_disabled`, `plugin_notification` |

294294| `SubagentStart` | agent type | `general-purpose`, `Explore`, `Plan`, custom agent names, or plugin-scoped names like `^my-plugin:reviewer$` |

295295| `PreCompact`, `PostCompact` | what triggered compaction | `manual`, `auto` |

296296| `PreModelSwitch`, `PostModelSwitch` | canonical name of the model the session switches to, as described under [PreModelSwitch](#premodelswitch) | `claude-opus-5`, `claude-opus-4-6\|claude-opus-5`, `.*opus.*` |

from line 2475

24752475| `permission_prompt` | Claude needs you to approve a tool use or a sandboxed command's [network request](https://code.claude.com/docs/en/sandboxing.md#network-isolation), and the prompt has waited about six seconds |

24762476| `idle_prompt` | Claude finished responding about 60 seconds ago and you haven't typed since |

24772477| `auth_success` | Authentication completes |

2478| `auth_storage_failure` | Your sign-in completes, but Claude Code can't save the new credentials to its [credential storage](https://code.claude.com/docs/en/authentication.md#credential-management). Fires in place of `auth_success` |

24782479| `elicitation_dialog` | An MCP server opens an elicitation form and you haven't typed for about six seconds |

24792480| `elicitation_url_dialog` | An MCP server asks you to open a browser URL and you haven't typed for about six seconds |

24802481| `elicitation_complete` | An MCP server reports that a [URL-mode elicitation](#elicitation-input) is complete |

from line 2487

24862487| `quota_auto_resume_disabled` | Claude Code ends its wait for a claude.ai usage limit without continuing your task: [`autoContinueAtUsageLimit`](https://code.claude.com/docs/en/settings-reference#autocontinueatusagelimit) turned off or the reset moved more than 24 hours away during a wait Claude Code started on its own, the continued task kept hitting the limit, or the continuation was blocked before it reached the model. Doesn't fire when you press `Esc` or `Ctrl+C`, or pick **Don't continue automatically** |

24872488| `plugin_notification` | A [mod](https://code.claude.com/docs/en/plugins/mods/api.md#show-something-without-starting-a-turn) raises a notification with `$.ui.notify`. The hook's `title` is the mod's name unless the mod set one |

24882489

2489The `quota_auto_resume_fired`, `quota_auto_resume_stale`, and `quota_auto_resume_disabled` types require Claude Code v2.1.234 or later.

2490The `quota_auto_resume_fired`, `quota_auto_resume_stale`, and `quota_auto_resume_disabled` types require Claude Code v2.1.234 or later. The `auth_storage_failure` type requires v2.1.288 or later.

24902491

24912492In terminal sessions, `permission_prompt` for a sandboxed command's network request requires Claude Code v2.1.246 or later.

24922493

from line 3806

38053806

38063807Runs after a user responds to an MCP elicitation. Hooks can observe, modify, or block the response before it is sent back to the MCP server.

38073808

3808When an [Elicitation](#elicitation) hook answers a request, Claude Code sends that answer to the server without running ElicitationResult hooks.

3809

3810The matcher field matches against the MCP server name.

3811

3812#### ElicitationResult input

3813

3814In addition to the [common input fields](#common-input-fields), ElicitationResult hooks receive `mcp_server_name`, `action`, and optional `mode`, `elicitation_id`, and `content` fields.

3815

3816```json theme={null}

3817{

3818 "session_i

3809When an [Elicitation](#elicitation) hook answers a request, Claude Code sends that answer to the server without running ElicitationResu

hooks-guide Changed · +4 / -3 lines

from line 173

173173> >

174174> > If you run Claude Code inside WSL, `powershell.exe` must be available on your `PATH` through Windows interop.

175175

176The empty `matcher` fires on all notification types. To fire only on specific events, set it to one of these values:

176The empty `matcher` fires on all notification types. To fire only on specific events, set it to a notification type, such as one of these:

177177

178178| Matcher | Fires when |

179179| :- | :- |

from line 180

180180| `permission_prompt` | Claude needs you to approve a tool use or a sandboxed command's [network request](https://code.claude.com/docs/en/sandboxing.md#network-isolation), and the prompt has waited about six seconds |

181181| `idle_prompt` | Claude finished responding about 60 seconds ago and you haven't typed since |

182182| `auth_success` | Authentication completes |

183| `auth_storage_failure` | Your sign-in completes, but Claude Code can't save the new credentials to its [credential storage](https://code.claude.com/docs/en/authentication.md#credential-management). Fires in place of `auth_success` |

183184| `elicitation_dialog` | An MCP server opens an elicitation form and you haven't typed for about six seconds |

184185| `elicitation_url_dialog` | An MCP server asks you to open a browser URL and you haven't typed for about six seconds |

185186| `elicitation_complete` | An MCP server reports that a [URL-mode elicitation](https://code.claude.com/docs/en/hooks.md#elicitation-input) is complete |

from line 194

193194

194195Claude Code times `permission_prompt` differently in a terminal and in Claude Desktop, the VS Code extension, and other hosts that answer permission requests through the Agent SDK. See [when each notification type fires](https://code.claude.com/docs/en/hooks.md#notification) for both timings.

195196

196The `quota_auto_resume_fired`, `quota_auto_resume_stale`, and `quota_auto_resume_disabled` matchers require Claude Code v2.1.234 or later.

197The `quota_auto_resume_fired`, `quota_auto_resume_stale`, and `quota_auto_resume_disabled` matchers require Claude Code v2.1.234 or later. The `auth_storage_failure` matcher requires v2.1.288 or later.

197198

198199In terminal sessions, `permission_prompt` for a sandboxed command's network request requires Claude Code v2.1.246 or later.

199200

from line 685

684685| `SessionStart` | how the session started | `startup`, `resume`, `clear`, `compact`, `fork` |

685686| `Setup` | which CLI flag triggered setup | `init`, `maintenance` |

686687| `SessionEnd` | why the session ended | `clear`, `resume`, `logout`, `prompt_input_exit`, `other` |

687| `Notification` | notification type | `permission_prompt`, `idle_prompt`, `auth_success`, `elicitation_dialog`, `elicitation_url_dialog`, `elicitation_complete`, `elicitation_response`, `agent_needs_input`, `agent_completed`, `quota_auto_resume_fired`, `quota_auto_resume_stale`, `quota_auto_resume_disabled`, `plugin_notification` |

688| `Notification` | notification type | `permission_prompt`, `idle_prompt`, `auth_success`, `auth_storage_failure`, `elicitation_dialog`, `elicitation_url_dialog`, `elicitation_complete`, `elicitation_response`, `agent_needs_input`, `agent_completed`, `quota_auto_resume_fired`, `quota_auto_resume_stale`, `quota_auto_resume_disabled`, `plugin_notification` |

688689| `SubagentStart` | agent type | `general-purpose`, `Explore`, `Plan`, or custom agent names |

689690| `PreCompact`, `PostCompact` | what triggered compaction | `manual`, `auto` |

690691| `PreModelSwitch`, `PostModelSwitch` | canonical name of the model the session switches to, as described under [PreModelSwitch](https://code.claude.com/docs/en/hooks.md#premodelswitch) | `claude-opus-5`, `claude-opus-4-6\|claude-opus-5`, `.*opus.*` |

settings-reference Changed · +8 / -4 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 442

442442

443443### `fastMode`

444444

445Turn [fast mode](https://code.claude.com/docs/en/fast-mode.md) on for sessions where it's available, for interactive work like rapid iteration or live debugging where you want speed at a higher cost per token. You don't usually edit this key by hand: running `/fast` writes `fastMode: true` to `~/.claude/settings.json`, and running it again to turn fast mode off removes the key. Fast mode runs only on Opus 5.5, Opus 5, and Opus 4.8: turning it on from another model switches you to Opus, and switching to an unsupported model turns it off. See [Switch models while fast mode is on](https://code.claude.com/docs/en/fast-mode.md#switch-models-while-fast-mode-is-on).

445Turn [fast mode](https://code.claude.com/docs/en/fast-mode.md) on for sessions where it's available, for interactive work such as rapid iteration or live debugging where you want speed at a higher cost per token. You don't usually edit this key yourself. Running `/fast` writes `fastMode: true` to `~/.claude/settings.json`, and running it again to turn fast mode off removes the key.

446446

447Only Opus 5.5, Opus 5, and Opus 4.8 support fast mode. Running `/fast` from another model switches you to Opus, and switching to an unsupported model turns fast mode off. See [Switch models while fast mode is on](https://code.claude.com/docs/en/fast-mode.md#switch-models-while-fast-mode-is-on).

448

447449* **Scope**: [`Any file`](#scopes)

448450* **Type**: Boolean

449451 * `true`: Claude Code turns fast mode on for sessions where it's available

from line 461

459461

460462### `fastModePerSessionOptIn`

461463

462Normally, running `/fast` saves [`fastMode`](#fastmode) to a person's user settings, so fast mode is on at the start of every later session. Set this key to `true` to stop that: a saved `fastMode: true` no longer turns fast mode on at session start, and each person has to run `/fast` in each session they want it. Claude Code leaves the `fastMode` key in their file, so turning this key off restores the old behavior.

464Normally, running `/fast` saves [`fastMode`](#fastmode) to a person's user settings, so new sessions on a supported model start with fast mode on. Set this key to `true` to stop that: a saved `fastMode: true` no longer turns fast mode on at session start, and each person runs `/fast` in each session they want it. Claude Code leaves `fastMode` in their file, so turning this key off restores the old behavior.

463465

464466Owners on Team or Enterprise plans can deploy it organization-wide through [server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md). When managed settings set the key, `/fast on` is refused outside interactive terminal sessions and reports that your organization has disabled fast mode. That covers [non-interactive mode](https://code.claude.com/docs/en/headless.md), the [VS Code extension](https://code.claude.com/docs/en/vs-code.md), and [cloud sessions](https://code.claude.com/docs/en/claude-code-on-the-web.md).

465467

from line 468

466468* **Scope**: [`Any file`](#scopes)

467469* **Type**: Boolean

468470 * `true`: a saved `fastMode: true` no longer turns fast mode on at session start, so each person runs `/fast` in each session they want it; a `fastMode: true` passed with `--settings` still counts for that session unless managed settings set this key

469 * `false`: a saved `fastMode: true` turns fast mode on at the start of every later session

471 * `false`: a saved `fastMode: true` turns fast mode on at the start of each new session on a supported model

470472* **Default**: `false`

471473

472474```json settings.json theme={null}

from line 3400

33983400

33993401To hide all attribution, set `attribution` to `false`. In a settings file that earlier versions also read, set [`commit`](#attribution-commit) and [`pr`](#attribution-pr) to empty strings and [`sessionUrl`](#attribution-sessionurl) to `false` instead.

34003402

3401This example replaces the commit attribution, removes pull request attribution, and drops

3403This example replaces the commit attribution, removes pull reques

vs-code Changed · +12 / -3 lines

from line 814

814814

815815### Run CLI in VS Code

816816

817To use the CLI while staying in VS Code, press `` Ctrl+` `` on Windows/Linux or `` Cmd+` `` on Mac to open the integrated terminal, then run `claude`. Starting `claude` doesn't install the extension. Without it, `/ide` in the integrated terminal reports "No available IDEs detected" and `/status` shows the IDE as "Not connected".

817To use the CLI while staying in VS Code, press `` Ctrl+` `` on Windows/Linux or `` Cmd+` `` on Mac to open the integrated terminal, then run `claude`.

818818

819819To get features like diff viewing and diagnostic sharing, connect the CLI to the extension from the integrated terminal or an external terminal:

820820

821* **Integrated terminal**: [install the extension](#install-the-extension), then start `claude`. The CLI connects automatically.

821* **Integrated terminal**: [install the extension](#install-the-extension), then start `claude`. The CLI connects automatically. Claude Code v2.1.318 or later doesn't install the extension for you, so until you install it, `/ide` reports "No available IDEs detected" and `/status` shows the IDE as "Not connected".

822822* **External terminal**: run `/ide` inside Claude Code to connect to VS Code. If VS Code is running without the extension, `/ide` installs it, unless you turned off [`autoInstallIdeExtension`](https://code.claude.com/docs/en/settings-reference#autoinstallideextension).

823823

824824Installing the extension does not put `claude` on your shell PATH. The extension bundles a private copy of the CLI for its chat panel, but typing `claude` in a terminal requires the [standalone CLI install](https://code.claude.com/docs/en/setup.md). Run the install once and the commands on this page, including `claude mcp add` and `claude --resume`, work in any terminal. If `claude` is still not found after installing, [verify your PATH](https://code.claude.com/docs/en/troubleshoot-install.md#verify-your-path).

from line 1087

108710872. Search for "Claude Code"

108810883. Click **Uninstall**

10891089

1090The extension stays uninstalled when you start `claude`. If you run `/ide` from an external terminal while VS Code is running, Claude Code reinstalls it. To stop that, set [`autoInstallIdeExtension`](https://code.claude.com/docs/en/settings-reference#autoinstallideextension) to `false` in `~/.claude.json`, or turn off **Auto-install IDE extension** in `/config` from the integrated terminal. You can also set the [`CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL`](https://code.claude.com/docs/en/env-vars) environment variable to `1`.

1090If you do either of these after uninstalling, the extension comes back:

1091

1092* Run `/ide` from an external terminal while VS Code is running

1093* Start `claude` in the integrated terminal on a Claude Code version before v2.1.318

1094

1095To keep the extension from coming back, do one of these, then uninstall it again if it already came back:

1096

1097* Set [`autoInstallIdeExtension`](https://code.claude.com/docs/en/settings-reference#autoinstallideextension) to `false` in `~/.claude.json`

1098* Set [`CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL`](https://code.claude.com/docs/en/env-vars#variables) to `1` under `env` in a [settings file](https://code.claude.com/docs/en/env-vars.md#in-settings-files)

1099* In the integrated terminal, turn off **Auto-install IDE extension** in `/config`

10911100

10921101To also remove extension data and reset all settings, delete the extension's storage directory for your platform.

10931102

artifacts Changed · +1 / -1 lines

from line 137

137137

138138* **Cloud session without network access**: for a [cloud environment](https://code.claude.com/docs/en/cloud-environments.md#access-levels), that's the **None** level. In [auto mode](https://code.claude.com/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode), the classifier can approve instead; in a [Cowork](https://claude.com/product/cowork) session, the approval is yours alone.

139139* **Another organization's public artifact**: Claude Code asks you first, even in auto mode. Where Claude Code can't ask you, such as in `bypassPermissions` mode, Claude can't read the artifact. Claude can read these artifacts only while [feature-flag fetching](https://code.claude.com/docs/en/env-vars.md#features-that-need-feature-flag-fetching) is on.

140* **Unconfirmed owner or network setting**: when Claude Code can't confirm who made the artifact, or can't confirm a cloud session's network setting, it asks, and your approval covers that one request.

140* **Unconfirmed owner or network setting**: when Claude Code can't confirm who made the artifact, or can't confirm a cloud session's network setting, it asks, and your approval covers that one request. In [auto mode](https://code.claude.com/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode), the classifier can approve or block the read instead of asking you.

141141* **Plan mode**: in [plan mode](https://code.claude.com/docs/en/permission-modes.md#analyze-before-you-edit-with-plan-mode), Claude Code asks before the Artifact tool reads an artifact someone else in your organization made.

142142

143143When Claude reads the artifact with WebFetch, WebFetch's own [prompting rules](https://code.claude.com/docs/en/tools-reference.md#webfetch-tool-behavior) still apply.

prompt-caching Changed · +1 / -1 lines

from line 99

9999[Fast mode](https://code.claude.com/docs/en/fast-mode.md) and standard speed keep separate caches, so after you turn fast mode on or off, the next request can't use what the other speed cached. The first time you turn fast mode on in a conversation, the next request reads the whole conversation so far uncached at [fast mode rates](https://code.claude.com/docs/en/fast-mode.md#understand-the-cost-tradeoff). To keep that cost small, turn it on at the start of a session.

100100

101101* If you turn it on while Claude is working, that turn finishes at standard speed, and you pay for any uncached read on your next turn's first request.

102* If your current model doesn't support fast mode, enabling fast mode also [switches you to Opus](https://code.claude.com/docs/en/fast-mode.md#toggle-fast-mode). That [model switch](#switching-models) starts a fresh cache on its own from the next request in the running turn.

102* If your current model doesn't support fast mode, running `/fast` also [switches you to Opus](https://code.claude.com/docs/en/fast-mode.md#toggle-fast-mode). That [model switch](#switching-models) starts a fresh cache on its own from the next request in the running turn.

103103

104104Each later toggle reads uncached whatever the speed you switch to doesn't have cached. Speed changes Claude Code makes on its own, such as the [fallback to standard speed](https://code.claude.com/docs/en/fast-mode.md#handle-rate-limits) after a rate limit and the return to fast mode later, count as toggles too.

105105

One read of Claude Code CLIclaude-code-20261106T040701Z

What this read moved

agent-sdk/python Changed · +5 / -12 lines

agent-sdk/typescript Changed · +20 / -8 lines

fast-mode Changed · +6 / -6 lines

hooks Changed · +3 / -2 lines

hooks-guide Changed · +4 / -3 lines

settings-reference Changed · +8 / -4 lines

vs-code Changed · +12 / -3 lines

artifacts Changed · +1 / -1 lines

prompt-caching Changed · +1 / -1 lines