Documentation — Spybara

en/agent-sdk/quickstart.md +12 −4

Details

204Your agent is ready. Run it with the following command:204Your agent is ready. Run it with the following command:

205 205

206<Tabs>206<Tabs>

207 <Tab title="Python">207 <Tab title="TypeScript">

208 ```bash theme={null}208 ```bash theme={null}

209 python3 agent.py209 npx tsx agent.ts

210 ```210 ```

211 </Tab>211 </Tab>

212 212

213 <Tab title="TypeScript">213 <Tab title="Python (uv)">

214 ```bash theme={null}214 ```bash theme={null}

215 npx tsx agent.ts215 uv run agent.py

216 ```

217 </Tab>

218

219 <Tab title="Python (pip)">

220 With your virtual environment still activated:

221

222 ```bash theme={null}

223 python agent.py

216 ```224 ```

217 </Tab>225 </Tab>

218</Tabs>226</Tabs>

en/agent-sdk/typescript.md +22 −3

Details

542 542

543Only some keys take effect mid-session:543Only some keys take effect mid-session:

544 544

545* **Applied on the next turn**: `model`, `effortLevel`, `ultracode`, `permissions`, `hooks`, `skillOverrides`, `fastMode`, `awaySummaryEnabled`545* **Applied on the next turn**: `model`, `effortLevel`, `ultracode`, `permissions`, `hooks`, `skillOverrides`, `fastMode`, `awaySummaryEnabled`, `agent`. Switching `agent` also applies that agent's model override, hooks, and system prompt on the next turn.

546* **No effect mid-session**: `agent` and the system prompt options. These are resolved once at startup, so the running session keeps the original value even though the call succeeds. To change them, start a new session.546* **No effect mid-session**: the system prompt options. These are resolved once at startup, so the running session keeps the original value even though the call succeeds. To change them, start a new session.

547 547

548The values are written to the flag-settings layer, the same layer the inline `settings` option of `query()` populates at startup. Flag settings sit near the top of the [settings precedence order](/en/settings#settings-precedence): they override user, project, and local settings, and only managed policy settings can override them. This is the same tier the [on-page precedence section](#settings-precedence) calls programmatic options.548The values are written to the flag-settings layer, the same layer the inline `settings` option of `query()` populates at startup. Flag settings sit near the top of the [settings precedence order](/en/settings#settings-precedence): they override user, project, and local settings, and only managed policy settings can override them. This is the same tier the [on-page precedence section](#settings-precedence) calls programmatic options.

549 549

603};603};

604```604```

605 605

606When a client sends `initialize` to a session that is already running, the control-response wrapper also carries an optional `pending_permission_requests` array. The field is on the response wrapper itself, not in the `SDKControlInitializeResponse` payload above. Each entry is a complete `control_request` message with the same `{ type: "control_request", request_id, request }` shape the session streams for permission requests while running.

607

608These are requests that were issued before the client connected and are still awaiting a reply, so read this array to surface in-flight permission prompts immediately; they will not be re-sent.

609

606### `AgentDefinition`610### `AgentDefinition`

607 611

608Configuration for a subagent defined programmatically.612Configuration for a subagent defined programmatically.

960 | SDKTaskProgressMessage964 | SDKTaskProgressMessage

961 | SDKTaskUpdatedMessage965 | SDKTaskUpdatedMessage

962 | SDKSessionStateChangedMessage966 | SDKSessionStateChangedMessage

967 | SDKCommandsChangedMessage

963 | SDKNotificationMessage968 | SDKNotificationMessage

964 | SDKFilesPersistedEvent969 | SDKFilesPersistedEvent

965 | SDKToolUseSummaryMessage970 | SDKToolUseSummaryMessage

989 994

990The `message` field is a [`BetaMessage`](https://platform.claude.com/docs/en/api/messages/create) from the Anthropic SDK. It includes fields like `id`, `content`, `model`, `stop_reason`, and `usage`.995The `message` field is a [`BetaMessage`](https://platform.claude.com/docs/en/api/messages/create) from the Anthropic SDK. It includes fields like `id`, `content`, `model`, `stop_reason`, and `usage`.

991 996

992`SDKAssistantMessageError` is one of: `'authentication_failed'`, `'oauth_org_not_allowed'`, `'billing_error'`, `'rate_limit'`, `'invalid_request'`, `'model_not_found'`, `'server_error'`, `'max_output_tokens'`, or `'unknown'`. `'model_not_found'` means the selected model doesn't exist or isn't available to your account or deployment.997`SDKAssistantMessageError` is one of: `'authentication_failed'`, `'oauth_org_not_allowed'`, `'billing_error'`, `'rate_limit'`, `'overloaded'`, `'invalid_request'`, `'model_not_found'`, `'server_error'`, `'max_output_tokens'`, or `'unknown'`. `'model_not_found'` means the selected model doesn't exist or isn't available to your account or deployment. `'overloaded'` means the API returned a 529 because the server is at capacity, as opposed to `'rate_limit'`, which is a 429 against your quota.

993 998

994### `SDKUserMessage`999### `SDKUserMessage`

995 1000

3242};3247};

3243```3248```

3244 3249

3250### `SDKCommandsChangedMessage`

3251

3252Emitted when the set of available commands changes mid-session, such as when skills are discovered as the agent enters a subdirectory. The `commands` array is the full updated list, so replace any cached command list with this payload. Calling `supportedCommands()` again is not equivalent: that method returns the snapshot captured at initialization and does not reflect mid-session changes.

3253

3254```typescript theme={null}

3255type SDKCommandsChangedMessage = {

3256 type: "system";

3257 subtype: "commands_changed";

3258 commands: SlashCommand[];

3259 uuid: UUID;

3260 session_id: string;

3261};

3262```

3263

3245### `SDKPromptSuggestionMessage`3264### `SDKPromptSuggestionMessage`

3246 3265

3247Emitted after each turn when `promptSuggestions` is enabled. Contains a predicted next user prompt.3266Emitted after each turn when `promptSuggestions` is enabled. Contains a predicted next user prompt.

en/agent-view.md +5 −1

Details

135 135

136The one-line summary in each row is generated by a [Haiku-class model](/en/model-config) so the row can tell you what the session is doing, what it needs, or what it produced without opening the transcript. While a session is actively working, the summary refreshes at most once every 15 seconds, plus once when each turn ends.136The one-line summary in each row is generated by a [Haiku-class model](/en/model-config) so the row can tell you what the session is doing, what it needs, or what it produced without opening the transcript. While a session is actively working, the summary refreshes at most once every 15 seconds, plus once when each turn ends.

137 137

138From v2.1.161, when the session is running two or more parallel work items, such as subagents, background shell commands, or monitors, a `done/total` count such as `2/5` appears before the summary text.

139

138Each refresh is one short Haiku-class request through your normal provider, billed and handled under the same [data usage terms](/en/data-usage) as the session itself. On third-party providers such as Bedrock, Vertex AI, Microsoft Foundry, and custom gateways, the request falls back to the session's main model when no Haiku model is configured. Set [`ANTHROPIC_DEFAULT_HAIKU_MODEL`](/en/model-config#environment-variables) to choose the model for these summaries on those providers.140Each refresh is one short Haiku-class request through your normal provider, billed and handled under the same [data usage terms](/en/data-usage) as the session itself. On third-party providers such as Bedrock, Vertex AI, Microsoft Foundry, and custom gateways, the request falls back to the session's main model when no Haiku model is configured. Set [`ANTHROPIC_DEFAULT_HAIKU_MODEL`](/en/model-config#environment-variables) to choose the model for these summaries on those providers.

139 141

140### Pull request status142### Pull request status

158 160

159Press `Space` on a selected row to open the peek panel. It shows what the session needs from you, its most recent output, and any pull requests it opened. Most of the time this is enough, and you never need to open the full transcript.161Press `Space` on a selected row to open the peek panel. It shows what the session needs from you, its most recent output, and any pull requests it opened. Most of the time this is enough, and you never need to open the full transcript.

160 162

163From v2.1.161, when the session is running parallel work items, the panel also names the longest-running one and how long it has been going, so you can see what the session is waiting on without attaching.

164

161Type a reply in the peek panel and press `Enter` to send it to that session. When the session is asking a multiple-choice question, the peek panel shows the options and you can press a number key to pick one. For other blocked sessions, press `Tab` to fill the input with a suggested reply you can edit before sending. Prefix a reply with `!` to send a Bash command instead.165Type a reply in the peek panel and press `Enter` to send it to that session. When the session is asking a multiple-choice question, the peek panel shows the options and you can press a number key to pick one. For other blocked sessions, press `Tab` to fill the input with a suggested reply you can edit before sending. Prefix a reply with `!` to send a Bash command instead.

162 166

163With [voice dictation](/en/voice-dictation) enabled, hold or tap your push-to-talk key while the reply input is focused to dictate a reply instead of typing it. The same works in the dispatch input at the bottom of agent view.167From v2.1.145, with [voice dictation](/en/voice-dictation) enabled, hold or tap your push-to-talk key while the reply input is focused to dictate a reply instead of typing it. The same works in the dispatch input at the bottom of agent view.

164 168

165Use `↑` and `↓` to peek at adjacent sessions without closing the panel, or `→` to attach.169Use `↑` and `↓` to peek at adjacent sessions without closing the panel, or `→` to attach.

166 170

en/amazon-bedrock.md +1 −0

Details

224 224

225* `AWS_REGION` is a required environment variable. Claude Code does not read from the `.aws` config file for this setting.225* `AWS_REGION` is a required environment variable. Claude Code does not read from the `.aws` config file for this setting.

226* When using Bedrock, the `/logout` command is unavailable since authentication is handled through AWS credentials.226* When using Bedrock, the `/logout` command is unavailable since authentication is handled through AWS credentials.

227* The WebSearch tool is not available on Bedrock. See [WebSearch tool behavior](/en/tools-reference#websearch-tool-behavior).

227* You can use settings files for environment variables like `AWS_PROFILE` that you don't want to leak to other processes. See [Settings](/en/settings) for more information.228* You can use settings files for environment variables like `AWS_PROFILE` that you don't want to leak to other processes. See [Settings](/en/settings) for more information.

228 229

229### 4. Pin model versions230### 4. Pin model versions

en/chrome.md +1 −1

Details

168 168

169### Extension not detected169### Extension not detected

170 170

171If Claude Code shows "Chrome extension not detected":171If Claude Code's setup-issues line lists `chrome`:

172 172

1731. Verify the Chrome extension is installed and enabled in `chrome://extensions`1731. Verify the Chrome extension is installed and enabled in `chrome://extensions`

1742. Verify Claude Code is up to date by running `claude --version`1742. Verify Claude Code is up to date by running `claude --version`

en/claude-directory.md +1 −1

Details

1556 1556

1557### Clear local data1557### Clear local data

1558 1558

1559Run `claude project purge` to delete the state Claude Code holds for one project:1559Run `claude project purge` to delete the state Claude Code holds for one project. The command requires Claude Code v2.1.124 or later. It deletes:

1560 1560

1561* Transcripts and auto memory under `projects/`1561* Transcripts and auto memory under `projects/`

1562* Per-session `tasks/`, `debug/`, and `file-history/` entries1562* Per-session `tasks/`, `debug/`, and `file-history/` entries

en/commands.md +3 −2

Details

50| `/autofix-pr [prompt]` | Spawn a [Claude Code on the web](/en/claude-code-on-the-web#auto-fix-pull-requests) session that watches the current branch's PR and pushes fixes when CI fails or reviewers leave comments. Detects the open PR from your checked-out branch with `gh pr view`; to watch a different PR, check out its branch first. By default the remote session is told to fix every CI failure and review comment; pass a prompt to give it different instructions, for example `/autofix-pr only fix lint and type errors`. Requires the `gh` CLI and access to [Claude Code on the web](/en/claude-code-on-the-web#who-can-use-claude-code-on-the-web) |50| `/autofix-pr [prompt]` | Spawn a [Claude Code on the web](/en/claude-code-on-the-web#auto-fix-pull-requests) session that watches the current branch's PR and pushes fixes when CI fails or reviewers leave comments. Detects the open PR from your checked-out branch with `gh pr view`; to watch a different PR, check out its branch first. By default the remote session is told to fix every CI failure and review comment; pass a prompt to give it different instructions, for example `/autofix-pr only fix lint and type errors`. Requires the `gh` CLI and access to [Claude Code on the web](/en/claude-code-on-the-web#who-can-use-claude-code-on-the-web) |

51| `/background [prompt]` | Detach the current session to run as a [background agent](/en/agent-view) and free this terminal. Pass a prompt to send one more instruction before detaching. Monitor the session with `claude agents`. Alias: `/bg` |51| `/background [prompt]` | Detach the current session to run as a [background agent](/en/agent-view) and free this terminal. Pass a prompt to send one more instruction before detaching. Monitor the session with `claude agents`. Alias: `/bg` |

52| `/batch <instruction>` | **[Skill](/en/skills#bundled-skills).** Orchestrate large-scale changes across a codebase in parallel. Researches the codebase, decomposes the work into 5 to 30 independent units, and presents a plan. Once approved, spawns one [background subagent](/en/sub-agents#run-subagents-in-foreground-or-background) per unit in an isolated [git worktree](/en/worktrees). Each subagent implements its unit, runs tests, and opens a pull request. Requires a git repository. Example: `/batch migrate src/ from Solid to React` |52| `/batch <instruction>` | **[Skill](/en/skills#bundled-skills).** Orchestrate large-scale changes across a codebase in parallel. Researches the codebase, decomposes the work into 5 to 30 independent units, and presents a plan. Once approved, spawns one [background subagent](/en/sub-agents#run-subagents-in-foreground-or-background) per unit in an isolated [git worktree](/en/worktrees). Each subagent implements its unit, runs tests, and opens a pull request. Requires a git repository. Example: `/batch migrate src/ from Solid to React` |

53| `/branch [name]` | Create a branch of the current conversation at this point. Switches you into the branch and preserves the original, which you can return to with `/resume`. Alias: `/fork`. When [`CLAUDE_CODE_FORK_SUBAGENT`](/en/env-vars) is set, `/fork` instead spawns a [forked subagent](/en/sub-agents#fork-the-current-conversation) and is no longer an alias for this command |53| `/branch [name]` | Create a branch of the current conversation at this point, so you can try a different direction without losing the conversation as it stands. Switches you into the branch and preserves the original, which you can return to with `/resume`. To hand a side task to a background subagent instead of switching into a copy yourself, use `/fork` |

54| `/btw <question>` | Ask a quick [side question](/en/interactive-mode#side-questions-with-%2Fbtw) without adding to the conversation |54| `/btw <question>` | Ask a quick [side question](/en/interactive-mode#side-questions-with-%2Fbtw) without adding to the conversation |

56| `/claude-api [migrate\|managed-agents-onboard]` | **[Skill](/en/skills#bundled-skills).** Load Claude API reference material for your project's language (Python, TypeScript, Java, Go, Ruby, C#, PHP, or cURL) and Managed Agents reference. Covers tool use, streaming, batches, structured outputs, and common pitfalls. Also activates automatically when your code imports `anthropic` or `@anthropic-ai/sdk`. Run `/claude-api migrate` to upgrade existing Claude API code to a newer model: Claude asks which files to scan and which model to target, then updates model IDs, thinking configuration, and other parameters that changed between versions. Run `/claude-api managed-agents-onboard` for an interactive walkthrough that creates a new Managed Agent from scratch |56| `/claude-api [migrate\|managed-agents-onboard]` | **[Skill](/en/skills#bundled-skills).** Load Claude API reference material for your project's language (Python, TypeScript, Java, Go, Ruby, C#, PHP, or cURL) and Managed Agents reference. Covers tool use, streaming, batches, structured outputs, and common pitfalls. Also activates automatically when your code imports `anthropic` or `@anthropic-ai/sdk`. Run `/claude-api migrate` to upgrade existing Claude API code to a newer model: Claude asks which files to scan and which model to target, then updates model IDs, thinking configuration, and other parameters that changed between versions. Run `/claude-api managed-agents-onboard` for an interactive walkthrough that creates a new Managed Agent from scratch |

75| `/fewer-permission-prompts` | **[Skill](/en/skills#bundled-skills).** Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project `.claude/settings.json` to reduce permission prompts |75| `/fewer-permission-prompts` | **[Skill](/en/skills#bundled-skills).** Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project `.claude/settings.json` to reduce permission prompts |

76| `/focus` | Toggle the focus view, which shows only your last prompt, a one-line tool-call summary with edit diffstats, and the final response. The selection persists across sessions; set [`viewMode`](/en/settings#available-settings) in settings to override it. Only available in [fullscreen rendering](/en/fullscreen) |76| `/focus` | Toggle the focus view, which shows only your last prompt, a one-line tool-call summary with edit diffstats, and the final response. The selection persists across sessions; set [`viewMode`](/en/settings#available-settings) in settings to override it. Only available in [fullscreen rendering](/en/fullscreen) |

77| `/fork <directive>` | {/* min-version: 2.1.161 */}Spawn a [forked subagent](/en/sub-agents#fork-the-current-conversation): a background subagent that inherits the full conversation and works on the directive while you keep going. Its result returns to your conversation when it finishes. To switch into a copy of the conversation yourself, use `/branch`. Before v2.1.161, `/fork` is an alias for `/branch` |

77| `/goal [condition\|clear]` | Set a [goal](/en/goal): Claude keeps working across turns until the condition is met. With no argument, shows the current or most recently achieved goal. `clear`, `stop`, `off`, `reset`, `none`, or `cancel` removes an active goal early |78| `/goal [condition\|clear]` | Set a [goal](/en/goal): Claude keeps working across turns until the condition is met. With no argument, shows the current or most recently achieved goal. `clear`, `stop`, `off`, `reset`, `none`, or `cancel` removes an active goal early |

78| `/heapdump` | Write a JavaScript heap snapshot and a memory breakdown to `~/Desktop`, or your home directory on Linux without a Desktop folder, for diagnosing high memory usage. See [troubleshooting](/en/troubleshooting#high-cpu-or-memory-usage) |79| `/heapdump` | Write a JavaScript heap snapshot and a memory breakdown to `~/Desktop`, or your home directory on Linux without a Desktop folder, for diagnosing high memory usage. See [troubleshooting](/en/troubleshooting#high-cpu-or-memory-usage) |

102| `/recap` | Generate a one-line summary of the current session on demand. See [Session recap](/en/interactive-mode#session-recap) for the automatic recap that appears after you've been away |103| `/recap` | Generate a one-line summary of the current session on demand. See [Session recap](/en/interactive-mode#session-recap) for the automatic recap that appears after you've been away |

103| `/release-notes` | View the changelog in an interactive version picker. Select a specific version to see its release notes, or choose to show all versions |104| `/release-notes` | View the changelog in an interactive version picker. Select a specific version to see its release notes, or choose to show all versions |

104| `/reload-plugins` | Reload all active [plugins](/en/plugins) to apply pending changes without restarting. Reports counts for each reloaded component and flags any load errors |105| `/reload-plugins` | Reload all active [plugins](/en/plugins) to apply pending changes without restarting. Reports counts for each reloaded component and flags any load errors |

105| `/reload-skills` | {/* min-version: 2.1.152 */}Re-scan [skill](/en/skills) and command directories so skills added or changed on disk during the session become available without restarting. Reports how many skills are available and how many were added or removed |106| `/reload-skills` | {/* min-version: 2.1.152 */}Re-scan [skill](/en/skills) and command directories so skills added or changed on disk during the session become available without restarting. Reports how many skills are available and how many were added or removed. Added in v2.1.152 |

107| `/remote-env` | Configure the default remote environment for [web sessions started with `--remote`](/en/claude-code-on-the-web#configure-your-environment) |108| `/remote-env` | Configure the default remote environment for [web sessions started with `--remote`](/en/claude-code-on-the-web#configure-your-environment) |

108| `/rename [name]` | Rename the current session and show the name on the prompt bar. Without a name, auto-generates one from conversation history |109| `/rename [name]` | Rename the current session and show the name on the prompt bar. Without a name, auto-generates one from conversation history |

en/context-window.md +13 −1

Details

1568 </>;1568 </>;

1569};1569};

1570 1570

1571Claude Code's context window holds everything Claude knows about your session: your instructions, the files it reads, its own responses, and content that never appears in your terminal. The timeline below walks through what loads and when. See [the written breakdown](#what-the-timeline-shows) for the same content as a list.1571Claude Code's context window holds everything Claude knows about your session: your instructions, the files it reads, its own responses, and content that never appears in your terminal. The timeline below plays a full session from startup to compaction: what loads before you type, what each file read, rule, and hook adds as Claude works, and how a subagent keeps large reads out of your context. See [the written breakdown](#what-the-timeline-shows) for the same content as a list.

1572 1572

1573<ContextWindow />1573<ContextWindow />

1574 1574

1599 1599

1600Skill bodies are re-injected after compaction, but large skills are truncated to fit the per-skill cap, and the oldest invoked skills are dropped once the total budget is exceeded. Truncation keeps the start of the file, so put the most important instructions near the top of `SKILL.md`.1600Skill bodies are re-injected after compaction, but large skills are truncated to fit the per-skill cap, and the oldest invoked skills are dropped once the total budget is exceeded. Truncation keeps the start of the file, so put the most important instructions near the top of `SKILL.md`.

1601 1601

1602## When your context fills up

1603

1604Claude Code compacts automatically as you approach the limit, so a full context window doesn't end your session. The automatic pass works the same way as the `/compact` step in the timeline. See [When context fills up](/en/how-claude-code-works#when-context-fills-up) for what it preserves.

1605

1606You can also act before the automatic pass runs:

1607

1608* **Compact with a focus**: run `/compact` with instructions, like `/compact focus on the auth bug fix`, before starting a long new task. The summary keeps what you choose instead of what the automatic pass guesses is important.

1609* **Clear between tasks**: run `/clear` when switching to unrelated work. Old conversation crowds out the files you need next and costs tokens on every message.

1610* **Delegate large reads**: send research to a [subagent](/en/sub-agents) so the file contents stay in its context window, not yours.

1611

1612If you need a larger window rather than a smaller conversation, Opus 4.6 and later, and Sonnet 4.6, support a 1 million token context window. See [Extended context](/en/model-config#extended-context) for availability by plan and how to select a `[1m]` model variant. Compaction works the same way at the larger limit.

1613

1602## Check your own session1614## Check your own session

1603 1615

1604The visualization uses representative numbers. To see your actual context usage at any point, run `/context` for a live breakdown by category with optimization suggestions. Run `/memory` to check which CLAUDE.md and auto memory files loaded at startup.1616The visualization uses representative numbers. To see your actual context usage at any point, run `/context` for a live breakdown by category with optimization suggestions. Run `/memory` to check which CLAUDE.md and auto memory files loaded at startup.

en/env-vars.md +8 −7

Details

150| `CLAUDE_CODE_DEBUG_LOGS_DIR` | Override the debug log file path. Despite the name, this is a file path, not a directory. Requires debug mode to be enabled separately via `--debug`, `/debug`, or the `DEBUG` environment variable: setting this variable alone does not enable logging. The [`--debug-file`](/en/cli-reference#cli-flags) flag does both at once. Defaults to `~/.claude/debug/<session-id>.txt` |150| `CLAUDE_CODE_DEBUG_LOGS_DIR` | Override the debug log file path. Despite the name, this is a file path, not a directory. Requires debug mode to be enabled separately via `--debug`, `/debug`, or the `DEBUG` environment variable: setting this variable alone does not enable logging. The [`--debug-file`](/en/cli-reference#cli-flags) flag does both at once. Defaults to `~/.claude/debug/<session-id>.txt` |

151| `CLAUDE_CODE_DEBUG_LOG_LEVEL` | Minimum log level written to the debug log file. Values: `verbose`, `debug` (default), `info`, `warn`, `error`. Set to `verbose` to include high-volume diagnostics like full status line command output, or raise to `error` to reduce noise |151| `CLAUDE_CODE_DEBUG_LOG_LEVEL` | Minimum log level written to the debug log file. Values: `verbose`, `debug` (default), `info`, `warn`, `error`. Set to `verbose` to include high-volume diagnostics like full status line command output, or raise to `error` to reduce noise |

152| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Set to `1` to disable [1M context window](/en/model-config#extended-context) support. When set, 1M model variants are unavailable in the model picker. Useful for enterprise environments with compliance requirements |152| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Set to `1` to disable [1M context window](/en/model-config#extended-context) support. When set, 1M model variants are unavailable in the model picker. Useful for enterprise environments with compliance requirements |

153| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/en/model-config#adjust-effort-level) on Opus 4.6 and Sonnet 4.6 and fall back to the fixed thinking budget controlled by `MAX_THINKING_TOKENS`. {/* min-version: 2.1.111 */}Has no effect on Opus 4.7 and later, which always use adaptive reasoning |153| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/en/model-config#adjust-effort-level) on Opus 4.6 and Sonnet 4.6 and fall back to the fixed thinking budget controlled by `MAX_THINKING_TOKENS`. {/* min-version: 2.1.111 */}From v2.1.111, has no effect on Opus 4.7 and later, which always use adaptive reasoning |

154| `CLAUDE_CODE_DISABLE_AGENT_VIEW` | Set to `1` to turn off [background agents and agent view](/en/agent-view): `claude agents`, `--bg`, `/background`, and the on-demand supervisor. Equivalent to the [`disableAgentView`](/en/settings#available-settings) setting |154| `CLAUDE_CODE_DISABLE_AGENT_VIEW` | Set to `1` to turn off [background agents and agent view](/en/agent-view): `claude agents`, `--bg`, `/background`, and the on-demand supervisor. Equivalent to the [`disableAgentView`](/en/settings#available-settings) setting |

155| `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN` | Set to `1` to disable [fullscreen rendering](/en/fullscreen) and use the classic main-screen renderer. The conversation stays in your terminal's native scrollback so `Cmd+f` and tmux copy mode work as usual. Takes precedence over `CLAUDE_CODE_NO_FLICKER` and the [`tui`](/en/settings#available-settings) setting. You can also switch with `/tui default`. Does not apply to background sessions opened from [agent view](/en/agent-view), which always use fullscreen rendering |155| `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN` | Set to `1` to disable [fullscreen rendering](/en/fullscreen) and use the classic main-screen renderer. The conversation stays in your terminal's native scrollback so `Cmd+f` and tmux copy mode work as usual. Takes precedence over `CLAUDE_CODE_NO_FLICKER` and the [`tui`](/en/settings#available-settings) setting. You can also switch with `/tui default`. Does not apply to background sessions opened from [agent view](/en/agent-view), which always use fullscreen rendering |

156| `CLAUDE_CODE_DISABLE_ATTACHMENTS` | Set to `1` to disable attachment processing. File mentions with `@` syntax are sent as plain text instead of being expanded into file content |156| `CLAUDE_CODE_DISABLE_ATTACHMENTS` | Set to `1` to disable attachment processing. File mentions with `@` syntax are sent as plain text instead of being expanded into file content |

174| `CLAUDE_CODE_DISABLE_VIRTUAL_SCROLL` | Set to `1` to disable virtual scrolling in [fullscreen rendering](/en/fullscreen) and render every message in the transcript. Use this if scrolling in fullscreen mode shows blank regions where messages should appear |174| `CLAUDE_CODE_DISABLE_VIRTUAL_SCROLL` | Set to `1` to disable virtual scrolling in [fullscreen rendering](/en/fullscreen) and render every message in the transcript. Use this if scrolling in fullscreen mode shows blank regions where messages should appear |

175| `CLAUDE_CODE_DISABLE_WORKFLOWS` | Set to `1` to disable [workflows](/en/workflows#turn-workflows-off). Equivalent to the [`disableWorkflows`](/en/settings#available-settings) setting |175| `CLAUDE_CODE_DISABLE_WORKFLOWS` | Set to `1` to disable [workflows](/en/workflows#turn-workflows-off). Equivalent to the [`disableWorkflows`](/en/settings#available-settings) setting |

176| `CLAUDE_CODE_EFFORT_LEVEL` | Set the effort level for supported models. Values: `low`, `medium`, `high`, `xhigh`, `max`, or `auto` to use the model default. Available levels depend on the model. Takes precedence over `/effort` and the `effortLevel` setting. See [Adjust effort level](/en/model-config#adjust-effort-level) |176| `CLAUDE_CODE_EFFORT_LEVEL` | Set the effort level for supported models. Values: `low`, `medium`, `high`, `xhigh`, `max`, or `auto` to use the model default. Available levels depend on the model. Takes precedence over `/effort` and the `effortLevel` setting. See [Adjust effort level](/en/model-config#adjust-effort-level) |

177| `CLAUDE_CODE_ENABLE_AUTO_MODE` | {/* min-version: 2.1.158 */}Set to `1` to make [auto mode](/en/permission-modes#eliminate-prompts-with-auto-mode) available on Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry. Has no effect on the Anthropic API, where auto mode is available by default. See [Enable auto mode on Bedrock, Vertex AI, or Foundry](/en/permission-modes#enable-auto-mode-on-bedrock-vertex-ai-or-foundry) |177| `CLAUDE_CODE_ENABLE_AUTO_MODE` | {/* min-version: 2.1.158 */}Set to `1` to make [auto mode](/en/permission-modes#eliminate-prompts-with-auto-mode) available on Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry. Requires Claude Code v2.1.158 or later. Has no effect on the Anthropic API, where auto mode is available by default. See [Enable auto mode on Bedrock, Vertex AI, or Foundry](/en/permission-modes#enable-auto-mode-on-bedrock-vertex-ai-or-foundry) |

178| `CLAUDE_CODE_ENABLE_AWAY_SUMMARY` | Override [session recap](/en/interactive-mode#session-recap) availability. Set to `0` to force recaps off regardless of the `/config` toggle. Set to `1` to force recaps on when [`awaySummaryEnabled`](/en/settings#available-settings) is `false`. Takes precedence over the setting and `/config` toggle |178| `CLAUDE_CODE_ENABLE_AWAY_SUMMARY` | Override [session recap](/en/interactive-mode#session-recap) availability. Set to `0` to force recaps off regardless of the `/config` toggle. Set to `1` to force recaps on when [`awaySummaryEnabled`](/en/settings#available-settings) is `false`. Takes precedence over the setting and `/config` toggle |

179| `CLAUDE_CODE_ENABLE_BACKGROUND_PLUGIN_REFRESH` | Set to `1` to refresh plugin state at turn boundaries in [non-interactive mode](/en/headless) after a background install completes. Off by default because the refresh changes the system prompt mid-session, which invalidates [prompt caching](/en/prompt-caching) for that turn |179| `CLAUDE_CODE_ENABLE_BACKGROUND_PLUGIN_REFRESH` | Set to `1` to refresh plugin state at turn boundaries in [non-interactive mode](/en/headless) after a background install completes. Off by default because the refresh changes the system prompt mid-session, which invalidates [prompt caching](/en/prompt-caching) for that turn |

180| `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL` | Set to `1` to route the "How is Claude doing?" session quality survey to your own [OpenTelemetry collector](/en/monitoring-usage) when Anthropic-bound nonessential traffic is blocked. Survey ratings are emitted only as OTEL events to your configured collector. No survey data is sent to Anthropic in this mode. Applies when `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`, `DISABLE_TELEMETRY`, or `DO_NOT_TRACK` is set, and has no effect otherwise. `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` and the organization product feedback policy take precedence |180| `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL` | Set to `1` to route the "How is Claude doing?" session quality survey to your own [OpenTelemetry collector](/en/monitoring-usage) when Anthropic-bound nonessential traffic is blocked. Survey ratings are emitted only as OTEL events to your configured collector. No survey data is sent to Anthropic in this mode. Applies when `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`, `DISABLE_TELEMETRY`, or `DO_NOT_TRACK` is set, and has no effect otherwise. `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` and the organization product feedback policy take precedence |

189| `CLAUDE_CODE_EXTRA_BODY` | JSON object to merge into the top level of every API request body. Useful for passing provider-specific parameters that Claude Code does not expose directly |189| `CLAUDE_CODE_EXTRA_BODY` | JSON object to merge into the top level of every API request body. Useful for passing provider-specific parameters that Claude Code does not expose directly |

190| `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS` | Override the default token limit for file reads. Useful when you need to read larger files in full |190| `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS` | Override the default token limit for file reads. Useful when you need to read larger files in full |

191| `CLAUDE_CODE_FORCE_SYNC_OUTPUT` | Set to `1` to force-enable DEC private mode 2026 [synchronized output](https://gist.github.com/christianparpart/d8a62cc1ab659194337d73e399004036) when your terminal supports it but is not auto-detected. Useful for emulators such as Emacs `eat` that implement BSU/ESU but do not reply to the capability probe. Has no effect under tmux |191| `CLAUDE_CODE_FORCE_SYNC_OUTPUT` | Set to `1` to force-enable DEC private mode 2026 [synchronized output](https://gist.github.com/christianparpart/d8a62cc1ab659194337d73e399004036) when your terminal supports it but is not auto-detected. Useful for emulators such as Emacs `eat` that implement BSU/ESU but do not reply to the capability probe. Has no effect under tmux |

192| `CLAUDE_CODE_FORK_SUBAGENT` | Set to `1` to enable [forked subagents](/en/sub-agents#fork-the-current-conversation). A forked subagent inherits the full conversation context from the main session instead of starting fresh. When enabled, `/fork` spawns a forked subagent rather than acting as an alias for [`/branch`](/en/commands), and all subagent spawns run in the background. Works in interactive mode and via the SDK or `claude -p` |192| `CLAUDE_CODE_FORK_SUBAGENT` | Set to `1` to make [forked subagents](/en/sub-agents#fork-the-current-conversation) the model's default: Claude spawns a fork, a subagent that inherits the full conversation context instead of starting fresh, whenever it would otherwise use the general-purpose subagent, and all subagent spawns run in the background. The explicit [`/fork`](/en/commands) command works without this variable. Works in interactive mode and via the SDK or `claude -p` |

193| `CLAUDE_CODE_GIT_BASH_PATH` | Windows only: path to the Git Bash executable (`bash.exe`). Use when Git Bash is installed but not in your PATH. See [Windows setup](/en/setup#set-up-on-windows) |193| `CLAUDE_CODE_GIT_BASH_PATH` | Windows only: path to the Git Bash executable (`bash.exe`). Use when Git Bash is installed but not in your PATH. See [Windows setup](/en/setup#set-up-on-windows) |

194| `CLAUDE_CODE_GLOB_HIDDEN` | Set to `false` to exclude dotfiles from results when Claude invokes the [Glob tool](/en/tools-reference#glob-tool-behavior). Included by default. Does not affect `@` file autocomplete, `ls`, Grep, or Read |194| `CLAUDE_CODE_GLOB_HIDDEN` | Set to `false` to exclude dotfiles from results when Claude invokes the [Glob tool](/en/tools-reference#glob-tool-behavior). Included by default. Does not affect `@` file autocomplete, `ls`, Grep, or Read |

195| `CLAUDE_CODE_GLOB_NO_IGNORE` | Set to `false` to make the [Glob tool](/en/tools-reference#glob-tool-behavior) respect `.gitignore` patterns. By default, Glob returns all matching files including gitignored ones. Does not affect `@` file autocomplete, which has its own [`respectGitignore` setting](/en/settings#available-settings) |195| `CLAUDE_CODE_GLOB_NO_IGNORE` | Set to `false` to make the [Glob tool](/en/tools-reference#glob-tool-behavior) respect `.gitignore` patterns. By default, Glob returns all matching files including gitignored ones. Does not affect `@` file autocomplete, which has its own [`respectGitignore` setting](/en/settings#available-settings) |

222| `CLAUDE_CODE_PLUGIN_PREFER_HTTPS` | Set to `1` to clone GitHub `owner/repo` shorthand sources over HTTPS instead of SSH. Applies to plugin install and update, and to `/plugin marketplace add` and `update`. Useful in CI runners, containers, or any environment without a configured SSH key for `github.com` |222| `CLAUDE_CODE_PLUGIN_PREFER_HTTPS` | Set to `1` to clone GitHub `owner/repo` shorthand sources over HTTPS instead of SSH. Applies to plugin install and update, and to `/plugin marketplace add` and `update`. Useful in CI runners, containers, or any environment without a configured SSH key for `github.com` |

223| `CLAUDE_CODE_PLUGIN_SEED_DIR` | Path to one or more read-only plugin seed directories, separated by `:` on Unix or `;` on Windows. Use this to bundle a pre-populated plugins directory into a container image. Claude Code registers marketplaces from these directories at startup and uses pre-cached plugins without re-cloning. See [Pre-populate plugins for containers](/en/plugin-marketplaces#pre-populate-plugins-for-containers) |223| `CLAUDE_CODE_PLUGIN_SEED_DIR` | Path to one or more read-only plugin seed directories, separated by `:` on Unix or `;` on Windows. Use this to bundle a pre-populated plugins directory into a container image. Claude Code registers marketplaces from these directories at startup and uses pre-cached plugins without re-cloning. See [Pre-populate plugins for containers](/en/plugin-marketplaces#pre-populate-plugins-for-containers) |

224| `CLAUDE_CODE_POWERSHELL_RESPECT_EXECUTION_POLICY` | Set to `1` to stop Claude Code from passing `-ExecutionPolicy Bypass` when spawning PowerShell for tool calls, hooks, and status line commands, and respect the machine's effective execution policy instead. By default Claude Code bypasses execution policy at process scope so `.ps1` scripts and module imports work on default-Restricted Windows installs. Process-scope bypass never overrides Group Policy `MachinePolicy` or `UserPolicy` regardless of this setting |224| `CLAUDE_CODE_POWERSHELL_RESPECT_EXECUTION_POLICY` | Set to `1` to stop Claude Code from passing `-ExecutionPolicy Bypass` when spawning PowerShell for tool calls, hooks, and status line commands, and respect the machine's effective execution policy instead. By default Claude Code bypasses execution policy at process scope so `.ps1` scripts and module imports work on default-Restricted Windows installs. Process-scope bypass never overrides Group Policy `MachinePolicy` or `UserPolicy` regardless of this setting |

225| `CLAUDE_CODE_PROPAGATE_TRACEPARENT` | {/* min-version: 2.1.152 */}Set to `1` to propagate W3C trace context when `ANTHROPIC_BASE_URL` points at a custom proxy. Propagation covers the `traceparent` header on model and HTTP MCP requests and the `TRACEPARENT` environment variable for Bash, PowerShell, and hook subprocesses. By default, propagation is enabled only when connected directly to the Anthropic API. See [Traces (beta)](/en/monitoring-usage#traces-beta) |225| `CLAUDE_CODE_PROPAGATE_TRACEPARENT` | {/* min-version: 2.1.152 */}Set to `1` to propagate W3C trace context when `ANTHROPIC_BASE_URL` points at a custom proxy. Propagation covers the `traceparent` header on model and HTTP MCP requests and the `TRACEPARENT` environment variable for Bash, PowerShell, and hook subprocesses. By default, propagation is enabled only when connected directly to the Anthropic API. Added in v2.1.152. See [Traces (beta)](/en/monitoring-usage#traces-beta) |

226| `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` | Set by host platforms that embed Claude Code and manage model provider routing on its behalf. When set, provider-selection, endpoint, and authentication variables such as `CLAUDE_CODE_USE_BEDROCK`, `ANTHROPIC_BASE_URL`, and `ANTHROPIC_API_KEY` in settings files are ignored so user settings cannot override the host's routing. The automatic telemetry opt-out for Bedrock, Vertex, and Foundry is also skipped, so telemetry follows the standard `DISABLE_TELEMETRY` opt-out. See [Default behaviors by API provider](/en/data-usage#default-behaviors-by-api-provider) |226| `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` | Set by host platforms that embed Claude Code and manage model provider routing on its behalf. When set, provider-selection, endpoint, and authentication variables such as `CLAUDE_CODE_USE_BEDROCK`, `ANTHROPIC_BASE_URL`, and `ANTHROPIC_API_KEY` in settings files are ignored so user settings cannot override the host's routing. The automatic telemetry opt-out for Bedrock, Vertex, and Foundry is also skipped, so telemetry follows the standard `DISABLE_TELEMETRY` opt-out. See [Default behaviors by API provider](/en/data-usage#default-behaviors-by-api-provider) |

227| `CLAUDE_CODE_PROXY_RESOLVES_HOSTS` | Set to `1` to allow the proxy to perform DNS resolution instead of the caller. Opt-in for environments where the proxy should handle hostname resolution |227| `CLAUDE_CODE_PROXY_RESOLVES_HOSTS` | Set to `1` to allow the proxy to perform DNS resolution instead of the caller. Opt-in for environments where the proxy should handle hostname resolution |

228| `CLAUDE_CODE_REMOTE` | Set automatically to `true` when Claude Code is running as a [cloud session](/en/claude-code-on-the-web). Read this from a hook or setup script to detect whether you are in a cloud environment |228| `CLAUDE_CODE_REMOTE` | Set automatically to `true` when Claude Code is running as a [cloud session](/en/claude-code-on-the-web). Read this from a hook or setup script to detect whether you are in a cloud environment |

253| `CLAUDE_CODE_SYNTAX_HIGHLIGHT` | Set to `false` to disable syntax highlighting in diff output. Useful when colors interfere with your terminal setup. To also disable highlighting in code blocks and file previews, use the [`syntaxHighlightingDisabled`](/en/settings) setting |253| `CLAUDE_CODE_SYNTAX_HIGHLIGHT` | Set to `false` to disable syntax highlighting in diff output. Useful when colors interfere with your terminal setup. To also disable highlighting in code blocks and file previews, use the [`syntaxHighlightingDisabled`](/en/settings) setting |

254| `CLAUDE_CODE_TASK_LIST_ID` | Share a task list across sessions. Set the same ID in multiple Claude Code instances to coordinate on a shared task list. See [Task list](/en/interactive-mode#task-list) |254| `CLAUDE_CODE_TASK_LIST_ID` | Share a task list across sessions. Set the same ID in multiple Claude Code instances to coordinate on a shared task list. See [Task list](/en/interactive-mode#task-list) |

255| `CLAUDE_CODE_TEAM_NAME` | Name of the agent team this teammate belongs to. Set automatically on [agent team](/en/agent-teams) members |255| `CLAUDE_CODE_TEAM_NAME` | Name of the agent team this teammate belongs to. Set automatically on [agent team](/en/agent-teams) members |

256| `CLAUDE_CODE_TMPDIR` | Override the temp directory used for internal temp files. Claude Code appends `/claude-{uid}/` (Unix) or `/claude/` (Windows) to this path. Default: `/tmp` on macOS, `os.tmpdir()` on Linux/Windows |256| `CLAUDE_CODE_TMPDIR` | Override the temp directory used for internal temp files. Claude Code appends `/claude-{uid}/` on Unix or `/claude/` on Windows to this path. Default: `/tmp` on macOS, `os.tmpdir()` on Linux and Windows. {/* min-version: 2.1.161 */}As of v2.1.161, on macOS and Linux, Bash subprocesses receive a short fallback `$TMPDIR` under the system default when your override is a long path, since some tools fail when temp paths get too long. Claude Code's own temp files always use your override |

257| `CLAUDE_CODE_TMUX_TRUECOLOR` | Set to `1` to allow 24-bit truecolor output inside tmux. By default, Claude Code clamps to 256 colors when `$TMUX` is set because tmux does not pass through truecolor escape sequences unless configured to. Set this after adding `set -ga terminal-overrides ',*:Tc'` to your `~/.tmux.conf`. See [Terminal configuration](/en/terminal-config) for other tmux settings |257| `CLAUDE_CODE_TMUX_TRUECOLOR` | Set to `1` to allow 24-bit truecolor output inside tmux. By default, Claude Code clamps to 256 colors when `$TMUX` is set because tmux does not pass through truecolor escape sequences unless configured to. Set this after adding `set -ga terminal-overrides ',*:Tc'` to your `~/.tmux.conf`. See [Terminal configuration](/en/terminal-config) for other tmux settings |

320| `OTEL_LOG_TOOL_DETAILS` | Set to `1` to include tool input arguments, MCP server names, raw error strings on tool failures, and other tool details in OpenTelemetry traces and logs. Disabled by default to protect PII. See [Monitoring](/en/monitoring-usage) |320| `OTEL_LOG_TOOL_DETAILS` | Set to `1` to include tool input arguments, MCP server names, raw error strings on tool failures, and other tool details in OpenTelemetry traces and logs. Disabled by default to protect PII. See [Monitoring](/en/monitoring-usage) |

321| `OTEL_LOG_USER_PROMPTS` | Set to `1` to include user prompt text in OpenTelemetry traces and logs. Disabled by default (prompts are redacted). See [Monitoring](/en/monitoring-usage) |321| `OTEL_LOG_USER_PROMPTS` | Set to `1` to include user prompt text in OpenTelemetry traces and logs. Disabled by default (prompts are redacted). See [Monitoring](/en/monitoring-usage) |

322| `OTEL_METRICS_INCLUDE_ACCOUNT_UUID` | Set to `false` to exclude account UUID from metrics attributes (default: included). See [Monitoring](/en/monitoring-usage) |322| `OTEL_METRICS_INCLUDE_ACCOUNT_UUID` | Set to `false` to exclude account UUID from metrics attributes (default: included). See [Monitoring](/en/monitoring-usage) |

323| `OTEL_METRICS_INCLUDE_ENTRYPOINT` | {/* min-version: 2.1.152 */}Set to `true` to include the session entrypoint in metrics attributes (default: excluded). See [Monitoring](/en/monitoring-usage) |323| `OTEL_METRICS_INCLUDE_ENTRYPOINT` | {/* min-version: 2.1.152 */}Set to `true` to include the session entrypoint in metrics attributes (default: excluded). Added in v2.1.152. See [Monitoring](/en/monitoring-usage) |

324| `OTEL_METRICS_INCLUDE_RESOURCE_ATTRIBUTES` | {/* min-version: 2.1.161 */}As of v2.1.161, Claude Code attaches `OTEL_RESOURCE_ATTRIBUTES` keys to metric datapoint labels. Set to `false` to exclude them (default: included). See [Monitoring](/en/monitoring-usage#multi-team-organization-support) |

324| `OTEL_METRICS_INCLUDE_SESSION_ID` | Set to `false` to exclude session ID from metrics attributes (default: included). See [Monitoring](/en/monitoring-usage) |325| `OTEL_METRICS_INCLUDE_SESSION_ID` | Set to `false` to exclude session ID from metrics attributes (default: included). See [Monitoring](/en/monitoring-usage) |

325| `OTEL_METRICS_INCLUDE_VERSION` | Set to `true` to include Claude Code version in metrics attributes (default: excluded). See [Monitoring](/en/monitoring-usage) |326| `OTEL_METRICS_INCLUDE_VERSION` | Set to `true` to include Claude Code version in metrics attributes (default: excluded). See [Monitoring](/en/monitoring-usage) |

326| `SLASH_COMMAND_TOOL_CHAR_BUDGET` | Override the character budget for skill metadata shown to the [Skill tool](/en/skills#control-who-invokes-a-skill). The budget scales dynamically at 1% of the context window, with a fallback of 8,000 characters. Legacy name kept for backwards compatibility |327| `SLASH_COMMAND_TOOL_CHAR_BUDGET` | Override the character budget for skill metadata shown to the [Skill tool](/en/skills#control-who-invokes-a-skill). The budget scales dynamically at 1% of the context window, with a fallback of 8,000 characters. Legacy name kept for backwards compatibility |

339| `VERTEX_REGION_CLAUDE_4_7_OPUS` | {/* min-version: 2.1.111 */}Override region for Claude Opus 4.7 when using Vertex AI |340| `VERTEX_REGION_CLAUDE_4_7_OPUS` | {/* min-version: 2.1.111 */}Override region for Claude Opus 4.7 when using Vertex AI. Added in v2.1.111 |

341 342

342Standard OpenTelemetry exporter variables (`OTEL_METRICS_EXPORTER`, `OTEL_LOGS_EXPORTER`, `OTEL_EXPORTER_OTLP_ENDPOINT`, `OTEL_EXPORTER_OTLP_PROTOCOL`, `OTEL_EXPORTER_OTLP_HEADERS`, `OTEL_METRIC_EXPORT_INTERVAL`, `OTEL_RESOURCE_ATTRIBUTES`, and signal-specific variants) are also supported. See [Monitoring](/en/monitoring-usage) for configuration details.343Standard OpenTelemetry exporter variables (`OTEL_METRICS_EXPORTER`, `OTEL_LOGS_EXPORTER`, `OTEL_EXPORTER_OTLP_ENDPOINT`, `OTEL_EXPORTER_OTLP_PROTOCOL`, `OTEL_EXPORTER_OTLP_HEADERS`, `OTEL_METRIC_EXPORT_INTERVAL`, `OTEL_RESOURCE_ATTRIBUTES`, and signal-specific variants) are also supported. See [Monitoring](/en/monitoring-usage) for configuration details.

en/fast-mode.md +1 −1

Details

64 64

65Fast mode pricing is flat across the full 1M token context window. For the standard Opus rate to compare against, see the [Claude pricing reference](https://platform.claude.com/docs/en/about-claude/pricing).65Fast mode pricing is flat across the full 1M token context window. For the standard Opus rate to compare against, see the [Claude pricing reference](https://platform.claude.com/docs/en/about-claude/pricing).

66 66

67When you switch into fast mode mid-conversation, you pay the full fast mode uncached input token price for the entire conversation context. This costs more than if you had enabled fast mode from the start.67The first time you enable fast mode in a conversation, you pay the full fast mode uncached input token price for the entire conversation context. The deeper into a conversation you are, the more this costs, so enabling fast mode from the start is cheaper. The cost applies once per conversation, so toggling fast mode off and on again later does not repeat it. For the mechanism, see [how fast mode interacts with the prompt cache](/en/prompt-caching#turning-on-fast-mode).

68 68

69## Decide when to use fast mode69## Decide when to use fast mode

70 70

en/fullscreen.md +19 −2

Details

149 149

150Mouse capture is the most common friction point, especially over SSH or inside tmux. When Claude Code captures mouse events, your terminal's native copy-on-select stops working. The selection you make with click-and-drag exists inside Claude Code, not in your terminal's selection buffer, so tmux copy mode, Kitty hints, and similar tools don't see it.150Mouse capture is the most common friction point, especially over SSH or inside tmux. When Claude Code captures mouse events, your terminal's native copy-on-select stops working. The selection you make with click-and-drag exists inside Claude Code, not in your terminal's selection buffer, so tmux copy mode, Kitty hints, and similar tools don't see it.

151 151

152Claude Code tries to write the selection to your clipboard, but the path it uses depends on your setup. Inside tmux it writes to the tmux paste buffer. Over SSH it falls back to OSC 52 escape sequences, which some terminals block by default. iTerm2 blocks them until you turn on Settings → General → Selection → Applications in terminal may access clipboard. Running [`/terminal-setup`](/en/terminal-config) in iTerm2 enables this for you. Claude Code prints a toast after each copy telling you which path it used.152Claude Code writes the selection to your system clipboard, and the path it uses depends on your setup. On a local session it runs a native clipboard tool:

153 153

154For a one-off native selection, hold your terminal's bypass modifier while you click and drag: `Option` in iTerm2, or `Shift` in most Linux and Windows terminals. The modifier tells your terminal to handle the selection itself instead of forwarding mouse events to Claude Code, so `Cmd+C` and your terminal's other copy shortcuts work on it.154* **macOS**: `pbcopy`

155* **Linux**: `wl-copy` on Wayland, or `xclip` or `xsel` on X11, whichever is installed. Claude Code writes both the clipboard and the PRIMARY selection, so middle-click paste works.

156* **Windows and WSL**: PowerShell `Set-Clipboard`

157

158Inside tmux it also writes to the tmux paste buffer. Over SSH it falls back to OSC 52 escape sequences. Claude Code prints a toast after each copy telling you which path it used.

159

160Some terminals block OSC 52 by default. iTerm2 blocks it until you turn on Settings → General → Selection → Applications in terminal may access clipboard; running [`/terminal-setup`](/en/terminal-config) in iTerm2 enables this for you.

161

162For a one-off native selection, the key to use depends on your terminal:

163

164* **Terminal.app**: `Fn`

165* **iTerm2**: `Option`

166* **VS Code, Cursor, and Devin Desktop**: `Shift`, or `Option` on macOS with the `terminal.integrated.macOptionClickForcesSelection` setting enabled

167* **Most other terminals**: `Shift`

168

169Hold that key while you click and drag. Your terminal handles the selection itself instead of passing it to Claude Code, so copy shortcuts like `Cmd+C` work on what you select. Claude Code also shows the correct key in its on-screen hint.

170

171Over SSH or inside tmux, Claude Code can't always detect the terminal you're connecting from, so the hint lists the candidate keys instead.

155 172

156If you rely on native selection all the time, set `CLAUDE_CODE_DISABLE_MOUSE=1` to opt out of mouse capture while keeping the flicker-free rendering and flat memory:173If you rely on native selection all the time, set `CLAUDE_CODE_DISABLE_MOUSE=1` to opt out of mouse capture while keeping the flicker-free rendering and flat memory:

157 174

en/headless.md +2 −2

Details

153When an API request fails with a retryable error, Claude Code emits a `system/api_retry` event before retrying. You can use this to surface retry progress or implement custom backoff logic.153When an API request fails with a retryable error, Claude Code emits a `system/api_retry` event before retrying. You can use this to surface retry progress or implement custom backoff logic.

154 154

156| ---------------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |156| ---------------- | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

163| `error` | string | error category: `authentication_failed`, `oauth_org_not_allowed`, `billing_error`, `rate_limit`, `invalid_request`, `model_not_found`, `server_error`, `max_output_tokens`, or `unknown` |163| `error` | string | error category: `authentication_failed`, `oauth_org_not_allowed`, `billing_error`, `rate_limit`, `overloaded`, `invalid_request`, `model_not_found`, `server_error`, `max_output_tokens`, or `unknown` |

166 166

en/hooks.md +3 −3

Details

191Each event type matches on a different field:191Each event type matches on a different field:

192 192

194| :------------------------------------------------------------------------------------------------------------------------------------------------ | :----------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------- |194| :------------------------------------------------------------------------------------------------------------------------------------------------ | :----------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

206| `StopFailure` | error type | `rate_limit`, `authentication_failed`, `oauth_org_not_allowed`, `billing_error`, `invalid_request`, `model_not_found`, `server_error`, `max_output_tokens`, `unknown` |206| `StopFailure` | error type | `rate_limit`, `overloaded`, `authentication_failed`, `oauth_org_not_allowed`, `billing_error`, `invalid_request`, `model_not_found`, `server_error`, `max_output_tokens`, `unknown` |

2136 2136

2137| Field | Description |2137| Field | Description |

2138| :----------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |2138| :----------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

2139| `error` | Error type: `rate_limit`, `authentication_failed`, `oauth_org_not_allowed`, `billing_error`, `invalid_request`, `model_not_found`, `server_error`, `max_output_tokens`, or `unknown` |2139| `error` | Error type: `rate_limit`, `overloaded`, `authentication_failed`, `oauth_org_not_allowed`, `billing_error`, `invalid_request`, `model_not_found`, `server_error`, `max_output_tokens`, or `unknown` |

2141| `last_assistant_message` | The rendered error text shown in the conversation. Unlike `Stop` and `SubagentStop`, where this field holds Claude's conversational output, for `StopFailure` it contains the API error string itself, such as `"API Error: Rate limit reached"` |2141| `last_assistant_message` | The rendered error text shown in the conversation. Unlike `Stop` and `SubagentStop`, where this field holds Claude's conversational output, for `StopFailure` it contains the API error string itself, such as `"API Error: Rate limit reached"` |

2142 2142

en/hooks-guide.md +2 −2

Details

619Each event type matches on a specific field:619Each event type matches on a specific field:

620 620

622| :-------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------- |622| :-------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

632| `StopFailure` | error type | `rate_limit`, `authentication_failed`, `oauth_org_not_allowed`, `billing_error`, `invalid_request`, `model_not_found`, `server_error`, `max_output_tokens`, `unknown` |632| `StopFailure` | error type | `rate_limit`, `overloaded`, `authentication_failed`, `oauth_org_not_allowed`, `billing_error`, `invalid_request`, `model_not_found`, `server_error`, `max_output_tokens`, `unknown` |

en/mcp.md +2 −0

Details

788 </Step>788 </Step>

789</Steps>789</Steps>

790 790

791From v2.1.161, connectors you have never signed in to are collapsed behind a `Show unused connectors` row at the end of the claude.ai section, so an organization-provisioned list doesn't fill the panel. Select the row to expand them. A connector you signed in to before stays visible even when it currently needs re-authentication.

792

791Claude.ai connectors are fetched only when your active [authentication method](/en/authentication#authentication-precedence) is your Claude.ai subscription. They are not loaded when `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, `apiKeyHelper`, or a third-party provider such as Bedrock or Vertex is active, even if you previously ran `/login`. If `/mcp` does not list a connector you added, run `/status` to confirm which authentication method is active, unset that environment variable or remove the `apiKeyHelper` setting, then run `/login` to select your Claude.ai account.793Claude.ai connectors are fetched only when your active [authentication method](/en/authentication#authentication-precedence) is your Claude.ai subscription. They are not loaded when `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, `apiKeyHelper`, or a third-party provider such as Bedrock or Vertex is active, even if you previously ran `/login`. If `/mcp` does not list a connector you added, run `/status` to confirm which authentication method is active, unset that environment variable or remove the `apiKeyHelper` setting, then run `/login` to select your Claude.ai account.

792 794

793A server you've added in Claude Code takes [precedence](#scope-hierarchy-and-precedence) over a claude.ai connector that points at the same URL. When this happens, `/mcp` lists the connector as hidden and shows how to remove the duplicate if you'd rather use the connector.795A server you've added in Claude Code takes [precedence](#scope-hierarchy-and-precedence) over a claude.ai connector that points at the same URL. When this happens, `/mcp` lists the connector as hidden and shows how to remove the duplicate if you'd rather use the connector.

en/monitoring-usage.md +8 −2

Details

107The following environment variables control which attributes are included in metrics to manage cardinality:107The following environment variables control which attributes are included in metrics to manage cardinality:

108 108

110| ----------------------------------- | --------------------------------------------------------------------- | ------------- | ------------------ |110| ------------------------------------------ | ------------------------------------------------------------------------------- | ------------- | ------------------ |

115 116

116These variables help control the cardinality of metrics, which affects storage requirements and query performance in your metrics backend. Lower cardinality generally means better performance and lower storage costs but less granular data for analysis.117These variables help control the cardinality of metrics, which affects storage requirements and query performance in your metrics backend. Lower cardinality generally means better performance and lower storage costs but less granular data for analysis.

117 118

303* Create team-specific dashboards304* Create team-specific dashboards

304* Set up alerts for specific teams305* Set up alerts for specific teams

305 306

307Claude Code attaches these values as attributes on every metric datapoint and event record, in addition to sending them in the OTLP resource block. Because most metrics backends expose datapoint attributes as queryable labels, you can group and filter metrics by your custom keys directly. Custom keys never override the [standard attributes](#standard-attributes) such as `user.id` or `session.id`: when a key collides, Claude Code keeps the built-in value.

308

309Each custom key becomes a label on every metric series, so high-cardinality values increase storage cost in your metrics backend. To send custom attributes in the resource block only and omit them from datapoint labels, set `OTEL_METRICS_INCLUDE_RESOURCE_ATTRIBUTES=false`. See [Metrics cardinality control](#metrics-cardinality-control).

310

306<Warning>311<Warning>

307 **Important formatting requirements for OTEL\_RESOURCE\_ATTRIBUTES:**312 **Important formatting requirements for OTEL\_RESOURCE\_ATTRIBUTES:**

308 313

384All metrics and events share these standard attributes:389All metrics and events share these standard attributes:

385 390

387| ------------------- | ----------------------------------------------------------------------------------------------------------- | --------------------------------------------------- |392| ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------- |

390| `app.entrypoint` | How the session was launched, such as `cli`, `sdk-cli`, `sdk-ts`, `sdk-py`, or `claude-vscode` | `OTEL_METRICS_INCLUDE_ENTRYPOINT` (default: false) |395| `app.entrypoint` | How the session was launched, such as `cli`, `sdk-cli`, `sdk-ts`, `sdk-py`, or `claude-vscode` | `OTEL_METRICS_INCLUDE_ENTRYPOINT` (default: false) |

402| Keys from `OTEL_RESOURCE_ATTRIBUTES` | Custom attributes you set, such as `department` or `team.id`. See [Multi-team organization support](#multi-team-organization-support) | `OTEL_METRICS_INCLUDE_RESOURCE_ATTRIBUTES` (default: true) |

397 403

398Events additionally include the following attributes. These are never attached to metrics because they would cause unbounded cardinality:404Events additionally include the following attributes. These are never attached to metrics because they would cause unbounded cardinality:

399 405

en/permission-modes.md +3 −3

Details

179 179

180If Claude Code reports auto mode as unavailable, one of these requirements is unmet; this is not a transient outage. A separate message that names a model and says auto mode "cannot determine the safety" of an action is a transient classifier outage; see the [error reference](/en/errors#auto-mode-cannot-determine-the-safety-of-an-action).180If Claude Code reports auto mode as unavailable, one of these requirements is unmet; this is not a transient outage. A separate message that names a model and says auto mode "cannot determine the safety" of an action is a transient classifier outage; see the [error reference](/en/errors#auto-mode-cannot-determine-the-safety-of-an-action).

181 181

182If you set `defaultMode: "auto"` in [settings](/en/settings#available-settings) and the session starts in `default` mode with no error, the setting is likely in `.claude/settings.json` or `.claude/settings.local.json`. Claude Code ignores `auto` from those files so a repository cannot grant itself auto mode. Move it to `~/.claude/settings.json`.182If you set `defaultMode: "auto"` in [settings](/en/settings#available-settings) and the session starts in `default` mode with no error, the setting is likely in `.claude/settings.json` or `.claude/settings.local.json`. Claude Code v2.1.142 and later ignore `auto` from those files so a repository cannot grant itself auto mode. Move it to `~/.claude/settings.json`.

183 183

184### Enable auto mode on Bedrock, Vertex AI, or Foundry184### Enable auto mode on Bedrock, Vertex AI, or Foundry

185 185

186On [Amazon Bedrock](/en/amazon-bedrock), [Google Cloud Vertex AI](/en/google-vertex-ai), and [Microsoft Foundry](/en/microsoft-foundry), auto mode does not appear in the `Shift+Tab` cycle until `CLAUDE_CODE_ENABLE_AUTO_MODE` is set to `1`. Only Claude Opus 4.7 and Opus 4.8 are supported on these providers.186On [Amazon Bedrock](/en/amazon-bedrock), [Google Cloud Vertex AI](/en/google-vertex-ai), and [Microsoft Foundry](/en/microsoft-foundry), auto mode does not appear in the `Shift+Tab` cycle until `CLAUDE_CODE_ENABLE_AUTO_MODE` is set to `1`. The variable works in Claude Code v2.1.158 and later. Only Claude Opus 4.7 and Opus 4.8 are supported on these providers.

187 187

188To enable it for one developer, add the variable to the `env` block in `~/.claude/settings.json`:188To enable it for one developer, add the variable to the `env` block in `~/.claude/settings.json`:

189 189

334* `.devcontainer`334* `.devcontainer`

335* `.yarn`335* `.yarn`

336* `.mvn`336* `.mvn`

337* `.claude`, except for `.claude/commands`, `.claude/agents`, `.claude/skills`, and `.claude/worktrees` where Claude routinely creates content337* `.claude`, except for `.claude/worktrees` where Claude stores its own git worktrees

338 338

339Protected files:339Protected files:

340 340

en/prompt-caching.md +11 −0

Details

58 58

59* [Switching models](#switching-models)59* [Switching models](#switching-models)

60* [Changing effort level](#changing-effort-level)60* [Changing effort level](#changing-effort-level)

61* [Turning on fast mode](#turning-on-fast-mode)

61* [Connecting or disconnecting an MCP server](#connecting-or-disconnecting-an-mcp-server)62* [Connecting or disconnecting an MCP server](#connecting-or-disconnecting-an-mcp-server)

62* [Enabling or disabling a plugin](#enabling-or-disabling-a-plugin)63* [Enabling or disabling a plugin](#enabling-or-disabling-a-plugin)

63* [Denying an entire tool](#denying-an-entire-tool)64* [Denying an entire tool](#denying-an-entire-tool)

74 75

75The cache is keyed by [effort level](/en/model-config#adjust-effort-level) as well as model, so switching with `/effort` means the next request reads the entire conversation history with no cache hits. Once a conversation has started, Claude Code shows a confirmation dialog before applying an effort change that would invalidate the cache. A change that resolves to the same level already in effect, such as setting the model's default explicitly, skips the dialog and keeps the cache.76The cache is keyed by [effort level](/en/model-config#adjust-effort-level) as well as model, so switching with `/effort` means the next request reads the entire conversation history with no cache hits. Once a conversation has started, Claude Code shows a confirmation dialog before applying an effort change that would invalidate the cache. A change that resolves to the same level already in effect, such as setting the model's default explicitly, skips the dialog and keeps the cache.

76 77

78### Turning on fast mode

80Enabling [fast mode](/en/fast-mode) adds a request header that is part of the cache key, so the next request reads the entire conversation history with no cache hits. Those uncached input tokens are billed at [fast mode rates](/en/fast-mode#understand-the-cost-tradeoff), which is why turning it on at the start of a session costs less than turning it on deep into a long one. Enabling fast mode from a non-Opus model also [switches your model](#switching-models), which starts a fresh cache on its own.

82The cost applies once per conversation. After the first fast mode turn, Claude Code keeps sending the header and varies only the request's speed setting, which is not part of the cache key. Turning fast mode off, the [automatic fallback to standard speed](/en/fast-mode#handle-rate-limits) after a rate limit, and turning it back on later all keep the cache. `/clear` and `/compact` reset this, since they rebuild the cache at those points anyway.

84<Note>

85 Keeping the header across toggles requires Claude Code v2.1.86 or later. On earlier versions, every fast mode toggle and rate-limit fallback invalidates the cache.

86</Note>

77### Connecting or disconnecting an MCP server88### Connecting or disconnecting an MCP server

78 89

79Tool definitions sit in the system prompt layer, so the cache invalidates when the set of tool definitions in the request changes between turns. Whether an [MCP server](/en/mcp) change does this depends on whether its tools are deferred by [tool search](/en/mcp#scale-with-mcp-tool-search) or loaded into the prefix:90Tool definitions sit in the system prompt layer, so the cache invalidates when the set of tool definitions in the request changes between turns. Whether an [MCP server](/en/mcp) change does this depends on whether its tools are deferred by [tool search](/en/mcp#scale-with-mcp-tool-search) or loaded into the prefix:

en/settings.md +6 −4

Details

168`settings.json` supports a number of options:168`settings.json` supports a number of options:

169 169

170| Key | Description | Example |170| Key | Description | Example |

171| :-------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------- |171| :-------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------- |

172| `agent` | Run the main thread as a named subagent, and set the default agent for sessions dispatched from `claude agents`. Applies that subagent's system prompt, tool restrictions, and model. See [Invoke subagents explicitly](/en/sub-agents#invoke-subagents-explicitly) | `"code-reviewer"` |172| `agent` | Run the main thread as a named subagent, and set the default agent for sessions dispatched from `claude agents`. Applies that subagent's system prompt, tool restrictions, and model. See [Invoke subagents explicitly](/en/sub-agents#invoke-subagents-explicitly) | `"code-reviewer"` |

173| `allowAllClaudeAiMcps` | (Managed settings only) Load claude.ai connectors alongside a deployed `managed-mcp.json`, which otherwise takes exclusive control and suppresses them. See [Managed MCP configuration](/en/managed-mcp) | `true` |173| `allowAllClaudeAiMcps` | (Managed settings only) Load claude.ai connectors alongside a deployed `managed-mcp.json`, which otherwise takes exclusive control and suppresses them. See [Managed MCP configuration](/en/managed-mcp) | `true` |

174| `allowedChannelPlugins` | (Managed settings only) Allowlist of channel plugins that may push messages. Replaces the default Anthropic allowlist when set. Undefined = fall back to the default, empty array = block all channel plugins. Requires `channelsEnabled: true`. See [Restrict which channel plugins can run](/en/channels#restrict-which-channel-plugins-can-run) | `[{ "marketplace": "claude-plugins-official", "plugin": "telegram" }]` |174| `allowedChannelPlugins` | (Managed settings only) Allowlist of channel plugins that may push messages. Replaces the default Anthropic allowlist when set. Undefined = fall back to the default, empty array = block all channel plugins. Requires `channelsEnabled: true`. See [Restrict which channel plugins can run](/en/channels#restrict-which-channel-plugins-can-run) | `[{ "marketplace": "claude-plugins-official", "plugin": "telegram" }]` |

213| `fastModePerSessionOptIn` | When `true`, fast mode does not persist across sessions. Each session starts with fast mode off, requiring users to enable it with `/fast`. The user's fast mode preference is still saved. See [Require per-session opt-in](/en/fast-mode#require-per-session-opt-in) | `true` |213| `fastModePerSessionOptIn` | When `true`, fast mode does not persist across sessions. Each session starts with fast mode off, requiring users to enable it with `/fast`. The user's fast mode preference is still saved. See [Require per-session opt-in](/en/fast-mode#require-per-session-opt-in) | `true` |

214| `feedbackSurveyRate` | Probability (0–1) that the [session quality survey](/en/data-usage#session-quality-surveys) appears when eligible. Set to `0` to suppress entirely, or set [`CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY`](/en/env-vars) in `env`. Useful when using Bedrock, Vertex, or Foundry where the default sample rate does not apply | `0.05` |214| `feedbackSurveyRate` | Probability (0–1) that the [session quality survey](/en/data-usage#session-quality-surveys) appears when eligible. Set to `0` to suppress entirely, or set [`CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY`](/en/env-vars) in `env`. Useful when using Bedrock, Vertex, or Foundry where the default sample rate does not apply | `0.05` |

215| `fileSuggestion` | Configure a custom script for `@` file autocomplete. See [File suggestion settings](#file-suggestion-settings) | `{"type": "command", "command": "~/.claude/file-suggestion.sh"}` |215| `fileSuggestion` | Configure a custom script for `@` file autocomplete. See [File suggestion settings](#file-suggestion-settings) | `{"type": "command", "command": "~/.claude/file-suggestion.sh"}` |

216| `forceLoginMethod` | Use `claudeai` to restrict login to Claude.ai accounts, `console` to restrict login to Claude Console (API usage billing) accounts. When set in managed settings, sessions authenticated by API key, `apiKeyHelper`, or a third-party provider are blocked at startup, since neither value can be satisfied without first-party OAuth | `claudeai` |216| `forceLoginMethod` | Use `claudeai` to restrict login to Claude.ai accounts, `console` to restrict login to Claude Console accounts. When set in managed settings, sessions authenticated by `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, or `apiKeyHelper` are blocked at startup, since neither value can be satisfied without first-party OAuth. Third-party provider sessions such as Bedrock, Vertex, and Foundry are not blocked: they authenticate against your cloud provider rather than Anthropic | `claudeai` |

217| `forceLoginOrgUUID` | Require login to belong to a specific organization. Accepts a single UUID string, which also pre-selects that organization during login, or an array of UUIDs where any listed organization is accepted without pre-selection. When set in managed settings, login fails if the authenticated account does not belong to a listed organization, and sessions authenticated by API key, `apiKeyHelper`, or a third-party provider are blocked at startup since organization membership cannot be verified for them. An empty array fails closed and blocks login with a misconfiguration message | `"xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"` or `["xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx", "yyyyyyyy-yyyy-yyyy-yyyy-yyyyyyyyyyyy"]` |217| `forceLoginOrgUUID` | Require login to belong to a specific Anthropic organization. Accepts a single UUID string, which also pre-selects that organization during login, or an array of UUIDs where any listed organization is accepted without pre-selection. When set in managed settings, login fails if the authenticated account does not belong to a listed organization, and sessions authenticated by `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, or `apiKeyHelper` are blocked at startup since organization membership cannot be verified for them. Third-party provider sessions such as Bedrock, Vertex, and Foundry are not blocked: use your cloud IAM to restrict which cloud accounts can be used. An empty array fails closed and blocks login with a misconfiguration message | `"xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"` or `["xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx", "yyyyyyyy-yyyy-yyyy-yyyy-yyyyyyyyyyyy"]` |

218| `forceRemoteSettingsRefresh` | (Managed settings only) Block CLI startup until remote managed settings are freshly fetched from the server. If the fetch fails, the CLI exits rather than continuing with cached or no settings. When not set, startup continues without waiting for remote settings. See [fail-closed enforcement](/en/server-managed-settings#enforce-fail-closed-startup) | `true` |218| `forceRemoteSettingsRefresh` | (Managed settings only) Block CLI startup until remote managed settings are freshly fetched from the server. If the fetch fails, the CLI exits rather than continuing with cached or no settings. When not set, startup continues without waiting for remote settings. See [fail-closed enforcement](/en/server-managed-settings#enforce-fail-closed-startup) | `true` |

219| `gcpAuthRefresh` | Custom script that refreshes GCP Application Default Credentials when they expire or cannot be loaded. See [advanced credential configuration](/en/google-vertex-ai#advanced-credential-configuration) | `gcloud auth application-default login` |219| `gcpAuthRefresh` | Custom script that refreshes GCP Application Default Credentials when they expire or cannot be loaded. See [advanced credential configuration](/en/google-vertex-ai#advanced-credential-configuration) | `gcloud auth application-default login` |

260| `viewMode` | Default transcript view mode on startup: `"default"`, `"verbose"`, or `"focus"`. Overrides the sticky `/focus` selection when set. The `--verbose` flag overrides this for one session | `"verbose"` |260| `viewMode` | Default transcript view mode on startup: `"default"`, `"verbose"`, or `"focus"`. Overrides the sticky `/focus` selection when set. The `--verbose` flag overrides this for one session | `"verbose"` |

261| `voice` | [Voice dictation](/en/voice-dictation) settings: `enabled` turns dictation on, `mode` selects `"hold"` or `"tap"`, and `autoSubmit` sends the prompt on key release in hold mode. Written automatically when you run `/voice`. Requires a Claude.ai account | `{ "enabled": true, "mode": "tap" }` |261| `voice` | [Voice dictation](/en/voice-dictation) settings: `enabled` turns dictation on, `mode` selects `"hold"` or `"tap"`, and `autoSubmit` sends the prompt on key release in hold mode. Written automatically when you run `/voice`. Requires a Claude.ai account | `{ "enabled": true, "mode": "tap" }` |

263| `workflowKeywordTriggerEnabled` | {/* min-version: 2.1.157 */}Whether the keyword `ultracode` in a prompt triggers a [dynamic workflow](/en/workflows#ask-for-a-workflow-in-your-prompt). Set to `false` to type the word without triggering one. The `ultracode` effort setting, `/workflows`, and saved workflow commands are unaffected. Default: `true`. Appears in `/config` as **Ultracode keyword trigger** | `false` |263| `workflowKeywordTriggerEnabled` | {/* min-version: 2.1.157 */}Whether the keyword `ultracode` in a prompt triggers a [dynamic workflow](/en/workflows#ask-for-a-workflow-in-your-prompt). Set to `false` to type the word without triggering one. The `ultracode` effort setting, `/workflows`, and saved workflow commands are unaffected. Default: `true`. Appears in `/config` as **Ultracode keyword trigger**. Added in v2.1.157; before v2.1.160 the trigger keyword was `workflow` | `false` |

264| `wslInheritsWindowsSettings` | (Windows managed settings only) When `true`, Claude Code on WSL reads managed settings from the Windows policy chain in addition to `/etc/claude-code`, with Windows sources taking priority. Only honored when set in the HKLM registry key or `C:\Program Files\ClaudeCode\managed-settings.json`, both of which require Windows admin to write. For HKCU policy to also apply on WSL, the flag must additionally be set in HKCU itself. Has no effect on native Windows | `true` |264| `wslInheritsWindowsSettings` | (Windows managed settings only) When `true`, Claude Code on WSL reads managed settings from the Windows policy chain in addition to `/etc/claude-code`, with Windows sources taking priority. Only honored when set in the HKLM registry key or `C:\Program Files\ClaudeCode\managed-settings.json`, both of which require Windows admin to write. For HKCU policy to also apply on WSL, the flag must additionally be set in HKCU itself. Has no effect on native Windows | `true` |

265 265

266### Global config settings266### Global config settings

694* `hostPattern`: regex pattern to match marketplace hosts (uses `hostPattern`)694* `hostPattern`: regex pattern to match marketplace hosts (uses `hostPattern`)

695* `settings`: inline marketplace declared directly in settings.json without a separate hosted repository (uses `name` and `plugins`)695* `settings`: inline marketplace declared directly in settings.json without a separate hosted repository (uses `name` and `plugins`)

696 696

697The `git` source type works with any git hosting service, including self-hosted GitLab and Bitbucket. Claude Code clones the repository with the same authentication that `git clone` would use on that machine: configured credential helpers, SSH keys, or a host-specific token environment variable. See [Private repositories](/en/plugin-marketplaces#private-repositories) for setup details.

698

697For `github` and `git` sources, set `"skipLfs": true` inside the `source` object (alongside `repo` or `url`) to skip Git LFS downloads when Claude Code clones or updates the marketplace repository. LFS pointer files remain as pointers instead of downloading their content. Use this when the repository contains large LFS objects unrelated to plugin content. {/* min-version: 2.1.153 */}Requires Claude Code v2.1.153 or later.699For `github` and `git` sources, set `"skipLfs": true` inside the `source` object (alongside `repo` or `url`) to skip Git LFS downloads when Claude Code clones or updates the marketplace repository. LFS pointer files remain as pointers instead of downloading their content. Use this when the repository contains large LFS objects unrelated to plugin content. {/* min-version: 2.1.153 */}Requires Claude Code v2.1.153 or later.

698 700

699Each marketplace entry also accepts an optional `autoUpdate` Boolean. Set `"autoUpdate": true` alongside `source` to make Claude Code refresh that marketplace and update its installed plugins at startup. When omitted, official Anthropic marketplaces default to `true` and all other marketplaces default to `false`. See [Configure auto-updates](/en/discover-plugins#configure-auto-updates).701Each marketplace entry also accepts an optional `autoUpdate` Boolean. Set `"autoUpdate": true` alongside `source` to make Claude Code refresh that marketplace and update its installed plugins at startup. When omitted, official Anthropic marketplaces default to `true` and all other marketplaces default to `false`. See [Configure auto-updates](/en/discover-plugins#configure-auto-updates).

en/sub-agents.md +4 −5

Details

711 711

712To disable all background task functionality, set the `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` environment variable to `1`. See [Environment variables](/en/env-vars).712To disable all background task functionality, set the `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` environment variable to `1`. See [Environment variables](/en/env-vars).

713 713

714When [fork mode](#fork-the-current-conversation) is enabled, every subagent spawn runs in the background regardless of the `background` field. Forks still surface permission prompts in your terminal as they occur; named subagents auto-deny anything that would prompt, as described above.714When [`CLAUDE_CODE_FORK_SUBAGENT`](#fork-the-current-conversation) is set, every subagent spawn runs in the background regardless of the `background` field. Forks still surface permission prompts in your terminal as they occur; named subagents auto-deny anything that would prompt, as described above.

715 715

716### Common patterns716### Common patterns

717 717

838## Fork the current conversation838## Fork the current conversation

839 839

840<Note>840<Note>

841 Forked subagents are experimental and require Claude Code v2.1.117 or later. Behavior and configuration may change in future releases. Enable them by setting the [`CLAUDE_CODE_FORK_SUBAGENT`](/en/env-vars) environment variable to `1`. The variable is honored in interactive mode and via the SDK or `claude -p`.841 Forked subagents require Claude Code v2.1.117 or later. {/* min-version: 2.1.161 */}From v2.1.161 the `/fork` command is enabled by default; on earlier versions it requires setting the [`CLAUDE_CODE_FORK_SUBAGENT`](/en/env-vars) environment variable to `1`. Making forks the model's *default* spawn behavior is experimental and may change in future releases; enable it by setting the same variable. The variable is honored in interactive mode and via the SDK or `claude -p`.

842</Note>842</Note>

843 843

844A fork is a subagent that inherits the entire conversation so far instead of starting fresh. This drops the input isolation that subagents otherwise provide: a fork sees the same system prompt, tools, model, and message history as the main session, so you can hand it a side task without re-explaining the situation. The fork's own tool calls still stay out of your conversation and only its final result comes back, so your main context window stays clean. Use a fork when a named subagent would need too much background to be useful, or when you want to try several approaches in parallel from the same starting point.844A fork is a subagent that inherits the entire conversation so far instead of starting fresh. This drops the input isolation that subagents otherwise provide: a fork sees the same system prompt, tools, model, and message history as the main session, so you can hand it a side task without re-explaining the situation. The fork's own tool calls still stay out of your conversation and only its final result comes back, so your main context window stays clean. Use a fork when a named subagent would need too much background to be useful, or when you want to try several approaches in parallel from the same starting point.

845 845

846Enabling fork mode changes Claude Code in three ways:846Setting `CLAUDE_CODE_FORK_SUBAGENT` changes Claude Code in two ways:

847 847

848* Claude spawns a fork whenever it would otherwise use the [general-purpose](#built-in-subagents) subagent. Named subagents such as Explore still spawn as before.848* Claude spawns a fork whenever it would otherwise use the [general-purpose](#built-in-subagents) subagent. Named subagents such as Explore still spawn as before.

849* Every subagent spawn runs in the [background](#run-subagents-in-foreground-or-background), whether it is a fork or a named subagent. Set `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` to `1` to keep spawns synchronous.849* Every subagent spawn runs in the [background](#run-subagents-in-foreground-or-background), whether it is a fork or a named subagent. Set `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` to `1` to keep spawns synchronous.

850* The `/fork` command spawns a fork instead of acting as an alias for [`/branch`](/en/commands).

851 850

852You can start a fork yourself with `/fork` followed by a directive. Claude Code names the fork from the first words of the directive. The following example forks the conversation to draft test cases while you continue with the implementation in the main session:851You can start a fork yourself with `/fork` followed by a directive, with or without the variable set. Claude Code names the fork from the first words of the directive. The following example forks the conversation to draft test cases while you continue with the implementation in the main session:

853 852

854```text theme={null}853```text theme={null}

855/fork draft unit tests for the parser changes so far854/fork draft unit tests for the parser changes so far

en/troubleshooting.md +4 −0

Details

57 57

58Restarting doesn't lose your conversation. Run `claude --resume` in the same directory to pick the session back up.58Restarting doesn't lose your conversation. Run `claude --resume` in the same directory to pick the session back up.

59 59

60### Garbled or corrupted text in an editor's integrated terminal

62If characters render as boxes, smears, or the wrong glyphs when running Claude Code in the VS Code, Cursor, or Devin Desktop integrated terminal, the terminal's GPU renderer is likely the cause. Run `/terminal-setup` inside Claude Code to set `terminal.integrated.gpuAcceleration` to `"off"`, or set it manually in your editor settings and reload the window. See [Terminal configuration](/en/terminal-config) for the other settings `/terminal-setup` writes.

60### Search and discovery issues64### Search and discovery issues

61 65

62If the Search tool, `@file` mentions, custom agents, or custom skills aren't finding files, the bundled `ripgrep` binary may not run on your system. Install your platform's `ripgrep` package and tell Claude Code to use it instead:66If the Search tool, `@file` mentions, custom agents, or custom skills aren't finding files, the bundled `ripgrep` binary may not run on your system. Install your platform's `ripgrep` package and tell Claude Code to use it instead:

en/whats-new/2026-w18.md +1 −1

Details

31<div className="digest-feature">31<div className="digest-feature">

32 <div className="digest-feature-header">32 <div className="digest-feature-header">

33 <span className="digest-feature-title">claude project purge</span>33 <span className="digest-feature-title">claude project purge</span>

~~34 <span className="digest-feature-pill">v2.1.126</span>~~34 <span className="digest-feature-pill">v2.1.124</span>

35 </div>35 </div>

36 36

37 <p className="digest-feature-lede">Delete all Claude Code state for a project: transcripts, tasks, file history, and the project's config entry. Supports `--dry-run` to preview, `-y`/`--yes` to skip confirmation, `-i`/`--interactive` to choose, and `--all` to clear every project.</p>37 <p className="digest-feature-lede">Delete all Claude Code state for a project: transcripts, tasks, file history, and the project's config entry. Supports `--dry-run` to preview, `-y`/`--yes` to skip confirmation, `-i`/`--interactive` to choose, and `--all` to clear every project.</p>

en/whats-new/2026-w19.md +3 −3

Details

7> Load plugins from .zip archives and URLs, search command history across every project with Ctrl+R, branch new worktrees from local HEAD or the remote default, and block actions unconditionally with auto mode hard deny rules.7> Load plugins from .zip archives and URLs, search command history across every project with Ctrl+R, branch new worktrees from local HEAD or the remote default, and block actions unconditionally with auto mode hard deny rules.

8 8

9<div className="digest-meta">9<div className="digest-meta">

~~10 <span>Releases <a href="/en/changelog#2-1-128">v2.1.128 → v2.1.136</a></span>~~10 <span>Releases <a href="/docs/en/changelog#2-1-128">v2.1.128 → v2.1.136</a></span>

11 <span>2 features · May 4–8</span>11 <span>2 features · May 4–8</span>

12</div>12</div>

13 13

24 claude --plugin-url https://example.com/my-plugin.zip24 claude --plugin-url https://example.com/my-plugin.zip

25 ```25 ```

26 26

~~27 <a className="digest-feature-link" href="/en/plugins">Plugins guide</a>~~27 <a className="digest-feature-link" href="/docs/en/plugins">Plugins guide</a>

28</div>28</div>

29 29

30<div className="digest-feature">30<div className="digest-feature">

35 35

36 <p className="digest-feature-lede"><code>Ctrl+R</code> reverse-search now defaults to all prompts across every project, restoring the behavior from before v2.1.124. Press <code>Ctrl+S</code> while searching to narrow back to the current project or session. Handy when you remember a command you ran in another repo last week and don't want to go digging for it.</p>36 <p className="digest-feature-lede"><code>Ctrl+R</code> reverse-search now defaults to all prompts across every project, restoring the behavior from before v2.1.124. Press <code>Ctrl+S</code> while searching to narrow back to the current project or session. Handy when you remember a command you ran in another repo last week and don't want to go digging for it.</p>

37 37

~~38 <a className="digest-feature-link" href="/en/interactive-mode#command-history">Interactive mode: command history</a>~~38 <a className="digest-feature-link" href="/docs/en/interactive-mode#command-history">Interactive mode: command history</a>

39</div>39</div>

40 40

41<div className="digest-wins">41<div className="digest-wins">

en/whats-new/2026-w20.md +5 −5

Details

7> Manage every Claude Code session from one screen with agent view, keep Claude working toward a goal until a condition holds, and run fast mode on Opus 4.7 by default.7> Manage every Claude Code session from one screen with agent view, keep Claude working toward a goal until a condition holds, and run fast mode on Opus 4.7 by default.

8 8

9<div className="digest-meta">9<div className="digest-meta">

~~10 <span>Releases <a href="/en/changelog#2-1-139">v2.1.139 → v2.1.142</a></span>~~10 <span>Releases <a href="/docs/en/changelog#2-1-139">v2.1.139 → v2.1.142</a></span>

11 <span>3 features · May 11–15</span>11 <span>3 features · May 11–15</span>

12</div>12</div>

13 13

29 claude agents29 claude agents

30 ```30 ```

31 31

~~32 <a className="digest-feature-link" href="/en/agent-view">Agent view</a>~~32 <a className="digest-feature-link" href="/docs/en/agent-view">Agent view</a>

33</div>33</div>

34 34

35<div className="digest-feature">35<div className="digest-feature">

50 > /goal all tests in test/auth pass and the lint step is clean50 > /goal all tests in test/auth pass and the lint step is clean

51 ```51 ```

52 52

~~53 <a className="digest-feature-link" href="/en/goal">Goals</a>~~53 <a className="digest-feature-link" href="/docs/en/goal">Goals</a>

54</div>54</div>

55 55

56<div className="digest-feature">56<div className="digest-feature">

59 <span className="digest-feature-pill">research preview</span>59 <span className="digest-feature-pill">research preview</span>

60 </div>60 </div>

61 61

62 <p className="digest-feature-lede"><code>/fast</code> now runs on Opus 4.7 by default instead of Opus 4.6. Fast mode is a high-speed Opus configuration: the same model quality at about 2.5x the speed for a higher per-token cost, useful for rapid iteration and live debugging. Pricing is unchanged at $30/$150 per MTok, the same as Opus 4.6 fast mode. To pin fast mode to Opus 4.6, set <code>CLAUDE\_CODE\_OPUS\_4\_6\_FAST\_MODE\_OVERRIDE=1</code>.</p>62 <p className="digest-feature-lede"><code>/fast</code> now runs on Opus 4.7 by default instead of Opus 4.6. Fast mode is a high-speed Opus configuration: the same model quality at about 2.5x the speed for a higher per-token cost, useful for rapid iteration and live debugging. Pricing is unchanged at \$30/\$150 per MTok, the same as Opus 4.6 fast mode. To pin fast mode to Opus 4.6, set <code>CLAUDE\_CODE\_OPUS\_4\_6\_FAST\_MODE\_OVERRIDE=1</code>.</p>

63 63

64 <Frame>64 <Frame>

65 <img className="w-full" src="https://mintcdn.com/claude-code/ITvjicPxe1SM3GX7/images/whats-new/fast-mode-opus-47.png?fit=max&auto=format&n=ITvjicPxe1SM3GX7&q=85&s=6b6d92f7748ce5328a1ee9a269fb1a87" alt="The Claude Code model picker showing Opus 4.7 Fast 1M as the default with the Fast toggle on" width="3840" height="2160" data-path="images/whats-new/fast-mode-opus-47.png" />65 <img className="w-full" src="https://mintcdn.com/claude-code/ITvjicPxe1SM3GX7/images/whats-new/fast-mode-opus-47.png?fit=max&auto=format&n=ITvjicPxe1SM3GX7&q=85&s=6b6d92f7748ce5328a1ee9a269fb1a87" alt="The Claude Code model picker showing Opus 4.7 Fast 1M as the default with the Fast toggle on" width="3840" height="2160" data-path="images/whats-new/fast-mode-opus-47.png" />

71 > /fast71 > /fast

72 ```72 ```

73 73

~~74 <a className="digest-feature-link" href="/en/fast-mode#use-fast-mode-on-opus-4-7">Fast mode on Opus 4.7</a>~~74 <a className="digest-feature-link" href="/docs/en/fast-mode#understand-the-cost-tradeoff">Fast mode on Opus 4.7</a>

75</div>75</div>

76 76

77<div className="digest-wins">77<div className="digest-wins">

en/whats-new/2026-w21.md +4 −4

Details

7> Use auto mode on the Pro plan and with Sonnet 4.6, see which skills, subagents, and MCP servers drive your plan limits in /usage, and review diffs with the new /code-review command.7> Use auto mode on the Pro plan and with Sonnet 4.6, see which skills, subagents, and MCP servers drive your plan limits in /usage, and review diffs with the new /code-review command.

8 8

9<div className="digest-meta">9<div className="digest-meta">

~~10 <span>Releases <a href="/en/changelog#2-1-143">v2.1.143 → v2.1.149</a></span>~~10 <span>Releases <a href="/docs/en/changelog#2-1-143">v2.1.143 → v2.1.149</a></span>

11 <span>1 feature · May 18–22</span>11 <span>1 feature · May 18–22</span>

12</div>12</div>

13 13

25 claude update25 claude update

26 ```26 ```

27 27

~~28 <a className="digest-feature-link" href="/en/permission-modes#eliminate-prompts-with-auto-mode">Auto mode</a>~~28 <a className="digest-feature-link" href="/docs/en/permission-modes#eliminate-prompts-with-auto-mode">Auto mode</a>

29</div>29</div>

30 30

31<div className="digest-wins">31<div className="digest-wins">

32 <p className="digest-wins-title">Other wins</p>32 <p className="digest-wins-title">Other wins</p>

33 33

34 <div className="digest-wins-grid">34 <div className="digest-wins-grid">

35 <div><a href="/en/costs#track-your-costs"><code>/usage</code></a> now shows a per-category breakdown of what's driving your plan limits, attributing recent usage to skills, subagents, plugins, and individual MCP servers</div>35 <div><a href="/docs/en/costs#track-your-costs"><code>/usage</code></a> now shows a per-category breakdown of what's driving your plan limits, attributing recent usage to skills, subagents, plugins, and individual MCP servers</div>

36 <div>"Extra usage" is renamed to "usage credits" across the CLI, and <code>/extra-usage</code> is now <code>/usage-credits</code>. The old name still works.</div>36 <div>"Extra usage" is renamed to "usage credits" across the CLI, and <code>/extra-usage</code> is now <code>/usage-credits</code>. The old name still works.</div>

37 <div>New <a href="/en/code-review"><code>/code-review</code></a> command reports correctness bugs at a chosen effort level such as <code>/code-review high</code>, and <code>--comment</code> posts findings as inline GitHub PR comments. <code>/simplify</code> remains as a separate cleanup-only review.</div>37 <div>New <a href="/docs/en/code-review"><code>/code-review</code></a> command reports correctness bugs at a chosen effort level such as <code>/code-review high</code>, and <code>--comment</code> posts findings as inline GitHub PR comments. <code>/simplify</code> remains as a separate cleanup-only review.</div>

38 <div>Background sessions now appear in <code>/resume</code> alongside interactive ones, marked with <code>bg</code>, and sessions pinned with <code>Ctrl+T</code> in <code>claude agents</code> stay alive when idle</div>38 <div>Background sessions now appear in <code>/resume</code> alongside interactive ones, marked with <code>bg</code>, and sessions pinned with <code>Ctrl+T</code> in <code>claude agents</code> stay alive when idle</div>

39 <div><code>claude agents --json</code> lists live sessions as JSON for scripting, such as status bars and session pickers</div>39 <div><code>claude agents --json</code> lists live sessions as JSON for scripting, such as status bars and session pickers</div>

40 <div>The PowerShell tool is now enabled by default on Windows for Bedrock, Vertex, and Foundry users; opt out with <code>CLAUDE\_CODE\_USE\_POWERSHELL\_TOOL=0</code></div>40 <div>The PowerShell tool is now enabled by default on Windows for Bedrock, Vertex, and Foundry users; opt out with <code>CLAUDE\_CODE\_USE\_POWERSHELL\_TOOL=0</code></div>

en/whats-new/2026-w22.md +5 −5

Details

7> Run Claude Code on Claude Opus 4.8, orchestrate large tasks with dynamic workflows, catch security issues with the security-guidance plugin, and use fast mode on Opus 4.8 at a lower price.7> Run Claude Code on Claude Opus 4.8, orchestrate large tasks with dynamic workflows, catch security issues with the security-guidance plugin, and use fast mode on Opus 4.8 at a lower price.

8 8

9<div className="digest-meta">9<div className="digest-meta">

~~10 <span>Releases <a href="/en/changelog#2-1-150">v2.1.150 → v2.1.157</a></span>~~10 <span>Releases <a href="/docs/en/changelog#2-1-150">v2.1.150 → v2.1.157</a></span>

11 <span>4 features · May 25–29</span>11 <span>4 features · May 25–29</span>

12</div>12</div>

13 13

29 > /model claude-opus-4-829 > /model claude-opus-4-8

30 ```30 ```

31 31

~~32 <a className="digest-feature-link" href="/en/model-config#available-models">Model configuration</a>~~32 <a className="digest-feature-link" href="/docs/en/model-config#available-models">Model configuration</a>

33</div>33</div>

34 34

35<div className="digest-feature">35<div className="digest-feature">

50 > create a workflow that migrates every internal fetch() call to the new HttpClient wrapper50 > create a workflow that migrates every internal fetch() call to the new HttpClient wrapper

51 ```51 ```

52 52

~~53 <a className="digest-feature-link" href="/en/workflows">Dynamic workflows</a>~~53 <a className="digest-feature-link" href="/docs/en/workflows">Dynamic workflows</a>

54</div>54</div>

55 55

56<div className="digest-feature">56<div className="digest-feature">

77 > /reload-plugins77 > /reload-plugins

78 ```78 ```

79 79

~~80 <a className="digest-feature-link" href="/en/security-guidance">Security guidance plugin</a>~~80 <a className="digest-feature-link" href="/docs/en/security-guidance">Security guidance plugin</a>

81</div>81</div>

82 82

83<div className="digest-feature">83<div className="digest-feature">

94 > /fast94 > /fast

95 ```95 ```

96 96

~~97 <a className="digest-feature-link" href="/en/fast-mode#understand-the-cost-tradeoff">Fast mode pricing</a>~~97 <a className="digest-feature-link" href="/docs/en/fast-mode#understand-the-cost-tradeoff">Fast mode pricing</a>

98</div>98</div>

99 99

100<div className="digest-wins">100<div className="digest-wins">

Documentation 2026-06-03 06:53 UTC to 2026-06-04 06:52 UTC