Documentation 2026-07-25 21:59 UTC to 2026-07-26 19:02 UTC

187* A subagent inherits the main session's extended thinking configuration. On earlier versions, extended thinking is disabled inside subagents regardless of the main session's setting.187* A subagent inherits the main session's extended thinking configuration. On earlier versions, extended thinking is disabled inside subagents regardless of the main session's setting.

188 188 

189<Note>189<Note>

190 {/* min-version: 2.1.217 */}By default, subagents can't spawn subagents of their own. To let them, set [`CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH`](/docs/en/env-vars) to the number of subagent layers you want below your main conversation, `2` or higher; see [nested subagents](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents). From Claude Code v2.1.172 through v2.1.216, subagents could nest by default, up to five layers.190 {/* min-version: 2.1.219 */}By default, subagents can spawn subagents of their own, up to three layers below the main conversation. {/* min-version: 2.1.217 */}To change the limit, set [`CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH`](/docs/en/env-vars) to the number of subagent layers you want below your main conversation, or `1` to turn nesting off; see [nested subagents](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents).

191 

192 Earlier versions used different defaults:

193 

194 * **v2.1.172 through v2.1.216**: subagents could nest by default, up to five layers deep, and the limit couldn't be changed.

195 * **v2.1.217 through v2.1.218**: the limit defaulted to one, so a subagent couldn't spawn its own unless you raised it; {/* min-version: 2.1.219 */}v2.1.219 raised the default to three.

191</Note>196</Note>

192 197 

193### Filesystem-based definition (alternative)198### Filesystem-based definition (alternative)

532 532 

533### Settings, plugins, and MCP servers533### Settings, plugins, and MCP servers

534 534 

535Agent view accepts the same configuration flags as `claude` for loading settings, plugins, MCP servers, and additional directories. Agent view applies each flag to itself and passes it through to every session you dispatch from it, so a plugin or MCP server you load this way is available in those sessions too.535Agent view accepts the same configuration flags as `claude` for loading settings, plugins, MCP servers, and additional directories. Agent view applies `--settings` and `--plugin-dir` to itself and passes every configuration flag through to the sessions you dispatch from it, so a plugin or MCP server you load this way is available in those sessions.

536 536 

537| Flag | Effect |537| Flag | Effect |

538| :----------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------- |538| :----------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------- |

807| v2.1.205 | {/* min-version: 2.1.205 */}The prompt footer's `←` hint in a regular `claude` session counts the background agents waiting on you, such as `← 2 agents`. Row summaries show the session's own one-line report, truncated at 64 columns, instead of a raw tool invocation or a `done/total` count; directory-grouped rows open with a colored state word. The peek panel opens with the full status sentence and, for a session waiting on you, its exact question above the reply input. Sessions that edit, comment on, close, or mark a pull request ready with `gh` are linked to it, not only ones that create or check out a pull request, a push links a pull request even when the local branch name doesn't match, and a pull request whose creating command's output exceeded the inline limit is linked too. A turn with no readable text keeps the session's previous state instead of flipping it back to `Working`. `claude attach` waits up to about 60 seconds for a session that's restarting, with a status line naming why, instead of failing. |807| v2.1.205 | {/* min-version: 2.1.205 */}The prompt footer's `←` hint in a regular `claude` session counts the background agents waiting on you, such as `← 2 agents`. Row summaries show the session's own one-line report, truncated at 64 columns, instead of a raw tool invocation or a `done/total` count; directory-grouped rows open with a colored state word. The peek panel opens with the full status sentence and, for a session waiting on you, its exact question above the reply input. Sessions that edit, comment on, close, or mark a pull request ready with `gh` are linked to it, not only ones that create or check out a pull request, a push links a pull request even when the local branch name doesn't match, and a pull request whose creating command's output exceeded the inline limit is linked too. A turn with no readable text keeps the session's previous state instead of flipping it back to `Working`. `claude attach` waits up to about 60 seconds for a session that's restarting, with a status line naming why, instead of failing. |

808| v2.1.203 | {/* min-version: 2.1.203 */}A gateway `ANTHROPIC_BASE_URL` exported in the dispatching shell reaches the sessions dispatched from it into that same directory when the supervisor shares that gateway environment, instead of being dropped while the API key exported alongside it was kept. The dispatching shell's `PATH` is applied to each session's worker. Pressing `←` while subagents are running waits for them instead of restarting them after ten seconds. The empty list always shows the section headers with a description under each. Typing `@` in the dispatch input also lists the launch repository's registered git worktrees that live inside its directory tree. An effort inherited from the `effortLevel` setting follows later edits to that setting instead of being fixed at dispatch. Opening a stopped session whose conversation is already open in another running session is refused with a message instead of failing the row. A command that isn't available in agent view leaves the typed text in the input. A `WorktreeCreate` hook that fails outside a git repository no longer blocks the session from editing files. |808| v2.1.203 | {/* min-version: 2.1.203 */}A gateway `ANTHROPIC_BASE_URL` exported in the dispatching shell reaches the sessions dispatched from it into that same directory when the supervisor shares that gateway environment, instead of being dropped while the API key exported alongside it was kept. The dispatching shell's `PATH` is applied to each session's worker. Pressing `←` while subagents are running waits for them instead of restarting them after ten seconds. The empty list always shows the section headers with a description under each. Typing `@` in the dispatch input also lists the launch repository's registered git worktrees that live inside its directory tree. An effort inherited from the `effortLevel` setting follows later edits to that setting instead of being fixed at dispatch. Opening a stopped session whose conversation is already open in another running session is refused with a message instead of failing the row. A command that isn't available in agent view leaves the typed text in the input. A `WorktreeCreate` hook that fails outside a git repository no longer blocks the session from editing files. |

809| v2.1.202 | {/* min-version: 2.1.202 */}A name set with `/rename` or `Ctrl+R` on a background session persists when the supervisor stops and restarts its process, instead of reverting to the name the session was dispatched with. |809| v2.1.202 | {/* min-version: 2.1.202 */}A name set with `/rename` or `Ctrl+R` on a background session persists when the supervisor stops and restarts its process, instead of reverting to the name the session was dispatched with. |

810| v2.1.200 | {/* min-version: 2.1.200 */}An older Claude Code version that rewrites the session list in `roster.json` preserves fields written by a newer version, matching the existing `state.json` guarantee, so sessions started by the newer version keep accepting input after the supervisor restarts. When you open a session that has stopped responding, the supervisor restarts its process and the session continues the interrupted response from where it left off. Agent view applies configuration flags placed after `agents`, such as `--plugin-dir`, to its own subagent and skill autocomplete in the dispatch input as well as dispatched sessions. |810| v2.1.200 | {/* min-version: 2.1.200 */}An older Claude Code version that rewrites the session list in `roster.json` preserves fields written by a newer version, matching the existing `state.json` guarantee, so sessions started by the newer version keep accepting input after the supervisor restarts. When you open a session that has stopped responding, the supervisor restarts its process and the session continues the interrupted response from where it left off. Agent view applies a `--plugin-dir` flag placed after `agents` to its own subagent and skill autocomplete in the dispatch input as well as dispatched sessions. |

811| v2.1.199 | {/* min-version: 2.1.199 */}A background session whose process exits before it finishes starting on a low-memory host shows `possibly low memory — free some up and retry` in its row status instead of only the bare exit reason. Backgrounding a session with `←` or `/background` carries its `/color` over to the new row. |811| v2.1.199 | {/* min-version: 2.1.199 */}A background session whose process exits before it finishes starting on a low-memory host shows `possibly low memory — free some up and retry` in its row status instead of only the bare exit reason. Backgrounding a session with `←` or `/background` carries its `/color` over to the new row. |

812| v2.1.198 | {/* min-version: 2.1.198 */}Agent view sends a notification through `preferredNotifChannel` when a background session needs input, finishes, or fails, and fires the `Notification` hook with the `agent_needs_input` or `agent_completed` type. `←` and `/exit` inside `claude attach <id>` return to agent view instead of exiting to the shell; `Ctrl+Z` returns to the shell. A background session that isolated its work in a worktree commits, pushes its own isolated branch, never `main` or `master`, and opens a draft pull request when it finishes instead of asking first. `/login` runs in agent view and opens the sign-in dialog. The `Background work is running` exit dialog offers `Move to background and exit`. The exit handoff also covers background subagents, which resume from their transcript on the next wake instead of being reported as failed. `claude --bg` combined with `-p` or `--print` is rejected with an error. The background session host requests macOS Local Network permission on first LAN access instead of failing with `connect: no route to host`. |812| v2.1.198 | {/* min-version: 2.1.198 */}Agent view sends a notification through `preferredNotifChannel` when a background session needs input, finishes, or fails, and fires the `Notification` hook with the `agent_needs_input` or `agent_completed` type. `←` and `/exit` inside `claude attach <id>` return to agent view instead of exiting to the shell; `Ctrl+Z` returns to the shell. A background session that isolated its work in a worktree commits, pushes its own isolated branch, never `main` or `master`, and opens a draft pull request when it finishes instead of asking first. `/login` runs in agent view and opens the sign-in dialog. The `Background work is running` exit dialog offers `Move to background and exit`. The exit handoff also covers background subagents, which resume from their transcript on the next wake instead of being reported as failed. `claude --bg` combined with `-p` or `--print` is rejected with an error. The background session host requests macOS Local Network permission on first LAN access instead of failing with `connect: no route to host`. |

813| v2.1.196 | {/* min-version: 2.1.196 */}A single `←` press backgrounds a foreground session; earlier versions required two presses, with a footer hint and a confirm. `--dangerously-skip-permissions` passed to `claude agents` shows the bypass disclaimer instead of being silently dropped. Interactive sessions you never named carry a default name such as `my-app-3f` in session listings and `claude agents --json`. Background shell commands and dynamic workflows survive the session's process being stopped, restarted, or updated, including on Windows; set `CLAUDE_CODE_DISABLE_BG_EXIT_HANDOFF=1` to turn the handoff off. A transcript misread as empty on restart is renamed with an `.orphaned-` suffix instead of deleted. |813| v2.1.196 | {/* min-version: 2.1.196 */}A single `←` press backgrounds a foreground session; earlier versions required two presses, with a footer hint and a confirm. `--dangerously-skip-permissions` passed to `claude agents` shows the bypass disclaimer instead of being silently dropped. Interactive sessions you never named carry a default name such as `my-app-3f` in session listings and `claude agents --json`. Background shell commands and dynamic workflows survive the session's process being stopped, restarted, or updated, including on Windows; set `CLAUDE_CODE_DISABLE_BG_EXIT_HANDOFF=1` to turn the handoff off. A transcript misread as empty on restart is renamed with an `.orphaned-` suffix instead of deleted. |

247| `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. Unlike `CLAUDE_CODE_NO_FLICKER`, which switches to [fullscreen rendering](/docs/en/fullscreen), this doesn't change the renderer |247| `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. Unlike `CLAUDE_CODE_NO_FLICKER`, which switches to [fullscreen rendering](/docs/en/fullscreen), this doesn't change the renderer |

248| `CLAUDE_CODE_FORK_SUBAGENT` | Set to `1` to let Claude spawn [forked subagents](/docs/en/sub-agents#fork-the-current-conversation), or `0` to disable them, overriding any server-side rollout. When enabled, Claude can request the `fork` subagent type to spawn a fork, a subagent that inherits the full conversation context instead of starting fresh. When Claude doesn't request a subagent type, it still gets the general-purpose subagent, and every subagent runs in the background. The explicit [`/subtask`](/docs/en/commands#all-commands) command, named `/fork` on v2.1.161 through v2.1.211, works without this variable; on v2.1.117 through v2.1.160, `/fork` is the forked-subagent command only when this variable is set to `1` or a server-side rollout enabled it. Works in interactive mode and via the SDK or `claude -p`. When [agent view is turned off](/docs/en/agent-view#turn-off-agent-view), `/subtask` isn't available and the command stays `/fork` |248| `CLAUDE_CODE_FORK_SUBAGENT` | Set to `1` to let Claude spawn [forked subagents](/docs/en/sub-agents#fork-the-current-conversation), or `0` to disable them, overriding any server-side rollout. When enabled, Claude can request the `fork` subagent type to spawn a fork, a subagent that inherits the full conversation context instead of starting fresh. When Claude doesn't request a subagent type, it still gets the general-purpose subagent, and every subagent runs in the background. The explicit [`/subtask`](/docs/en/commands#all-commands) command, named `/fork` on v2.1.161 through v2.1.211, works without this variable; on v2.1.117 through v2.1.160, `/fork` is the forked-subagent command only when this variable is set to `1` or a server-side rollout enabled it. Works in interactive mode and via the SDK or `claude -p`. When [agent view is turned off](/docs/en/agent-view#turn-off-agent-view), `/subtask` isn't available and the command stays `/fork` |

249| `CLAUDE_CODE_FORWARD_SUBAGENT_TEXT` | {/* min-version: 2.1.211 */}Set to `1` to emit [subagent](/docs/en/sub-agents) text and thinking blocks in `claude -p --output-format stream-json` output, the same behavior as the [`--forward-subagent-text`](/docs/en/cli-reference#cli-flags) flag. Use the variable when a harness invokes `claude` and can't pass the flag itself. Unlike the flag, which exits with an error outside non-interactive mode with stream-json output, the variable is ignored there so that nested invocations keep working when it's set process-wide. Requires Claude Code v2.1.211 or later |249| `CLAUDE_CODE_FORWARD_SUBAGENT_TEXT` | {/* min-version: 2.1.211 */}Set to `1` to emit [subagent](/docs/en/sub-agents) text and thinking blocks in `claude -p --output-format stream-json` output, the same behavior as the [`--forward-subagent-text`](/docs/en/cli-reference#cli-flags) flag. Use the variable when a harness invokes `claude` and can't pass the flag itself. Unlike the flag, which exits with an error outside non-interactive mode with stream-json output, the variable is ignored there so that nested invocations keep working when it's set process-wide. Requires Claude Code v2.1.211 or later |

250| `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](/docs/en/setup#set-up-on-windows) |250| `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. {/* min-version: 2.1.219 */}If the path doesn't exist or the file isn't named `bash.exe`, `sh.exe`, `bash`, or `sh`, Claude Code ignores the variable and auto-detects Git Bash as if it were unset, logging a warning visible with `--debug`. Before v2.1.219, Claude Code exited at startup when the path didn't exist, and used any existing file as the shell without checking that it was bash or sh. See [Windows setup](/docs/en/setup#set-up-on-windows) |

251| `CLAUDE_CODE_GLOB_HIDDEN` | Set to `false` to exclude dotfiles from results when Claude invokes the [Glob tool](/docs/en/tools-reference#glob-tool-behavior). Included by default. Does not affect `@` file autocomplete, `ls`, Grep, or Read |251| `CLAUDE_CODE_GLOB_HIDDEN` | Set to `false` to exclude dotfiles from results when Claude invokes the [Glob tool](/docs/en/tools-reference#glob-tool-behavior). Included by default. Does not affect `@` file autocomplete, `ls`, Grep, or Read |

252| `CLAUDE_CODE_GLOB_NO_IGNORE` | Set to `false` to make the [Glob tool](/docs/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](/docs/en/settings#available-settings) |252| `CLAUDE_CODE_GLOB_NO_IGNORE` | Set to `false` to make the [Glob tool](/docs/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](/docs/en/settings#available-settings) |

253| `CLAUDE_CODE_GLOB_TIMEOUT_SECONDS` | Timeout in seconds for Glob tool file discovery. Defaults to 20 seconds on most platforms and 60 seconds on WSL |253| `CLAUDE_CODE_GLOB_TIMEOUT_SECONDS` | Timeout in seconds for Glob tool file discovery. Defaults to 20 seconds on most platforms and 60 seconds on WSL |

260| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Set the maximum number of output tokens for most requests. Defaults and caps vary by model; see [max output tokens](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison). Increasing this value reduces the effective context window available before [auto-compaction](/docs/en/costs#reduce-token-usage) triggers |260| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Set the maximum number of output tokens for most requests. Defaults and caps vary by model; see [max output tokens](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison). Increasing this value reduces the effective context window available before [auto-compaction](/docs/en/costs#reduce-token-usage) triggers |

261| `CLAUDE_CODE_MAX_RETRIES` | Override the number of times to retry failed API requests (default: 10). {/* min-version: 2.1.186 */}Capped at 15 as of v2.1.186; {/* min-version: 2.1.199 */}as of v2.1.199, `CLAUDE_CODE_RETRY_WATCHDOG` raises the default and removes the cap. For unattended sessions that need to wait through longer outages, set `CLAUDE_CODE_RETRY_WATCHDOG` instead |261| `CLAUDE_CODE_MAX_RETRIES` | Override the number of times to retry failed API requests (default: 10). {/* min-version: 2.1.186 */}Capped at 15 as of v2.1.186; {/* min-version: 2.1.199 */}as of v2.1.199, `CLAUDE_CODE_RETRY_WATCHDOG` raises the default and removes the cap. For unattended sessions that need to wait through longer outages, set `CLAUDE_CODE_RETRY_WATCHDOG` instead |

262| `CLAUDE_CODE_MAX_SUBAGENTS_PER_SESSION` | {/* min-version: 2.1.212 */}Cap on the number of [subagents](/docs/en/sub-agents#session-subagent-limit) one session can spawn with the Agent tool (default: 200). When Claude reaches the cap, spawning another subagent fails with an error telling Claude to finish the remaining work directly. Accepts a positive whole number in plain digits with no upper bound; this variable doesn't take the scientific notation or digit-separator spellings. Anything else is ignored and the default applies, so the cap can be raised but not turned off. Requires Claude Code v2.1.212 or later |262| `CLAUDE_CODE_MAX_SUBAGENTS_PER_SESSION` | {/* min-version: 2.1.212 */}Cap on the number of [subagents](/docs/en/sub-agents#session-subagent-limit) one session can spawn with the Agent tool (default: 200). When Claude reaches the cap, spawning another subagent fails with an error telling Claude to finish the remaining work directly. Accepts a positive whole number in plain digits with no upper bound; this variable doesn't take the scientific notation or digit-separator spellings. Anything else is ignored and the default applies, so the cap can be raised but not turned off. Requires Claude Code v2.1.212 or later |

263| `CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH` | {/* min-version: 2.1.217 */}Number of [subagent layers](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents) allowed below the main conversation (default: 1). At the default, subagents can't spawn their own subagents; set `2` or higher to allow it. Accepts a positive whole number in plain digits; anything else is ignored, so the limit can be raised but not turned off. Requires Claude Code v2.1.217 or later |263| `CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH` | {/* min-version: 2.1.217 */}Number of [subagent layers](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents) allowed below the main conversation {/* min-version: 2.1.219 */}(default: 3). At the default, subagents can spawn their own subagents, and a subagent at the third layer can't spawn further; set `1` to turn nesting off. In v2.1.217 through v2.1.218, the default was 1, so a subagent couldn't spawn its own unless you raised the limit; v2.1.219 raised the default to 3. Accepts a positive whole number in plain digits; anything else is ignored, so the limit can be adjusted but not removed. Requires Claude Code v2.1.217 or later |

264| `CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY` | Maximum number of read-only tools and subagents that can execute in parallel (default: 10). Higher values increase parallelism but consume more resources |264| `CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY` | Maximum number of read-only tools and subagents that can execute in parallel (default: 10). Higher values increase parallelism but consume more resources |

265| `CLAUDE_CODE_MAX_TURNS` | Cap the number of agentic turns when no explicit limit is passed. Equivalent to passing [`--max-turns`](/docs/en/cli-reference#cli-flags), which takes precedence when both are set. A value that is not a positive integer is rejected at startup with an error rather than treated as no cap |265| `CLAUDE_CODE_MAX_TURNS` | Cap the number of agentic turns when no explicit limit is passed. Equivalent to passing [`--max-turns`](/docs/en/cli-reference#cli-flags), which takes precedence when both are set. A value that is not a positive integer is rejected at startup with an error rather than treated as no cap |

266| `CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION` | {/* min-version: 2.1.212 */}Cap on the total number of [WebSearch](/docs/en/tools-reference#websearch-tool-behavior) calls one session can make (default: 200). When Claude reaches the cap, further WebSearch calls return a notice telling it to continue with the information it already gathered. Accepts a positive whole number with no upper bound. Anything else is ignored and the default applies, so the cap can be raised but not turned off. Requires Claude Code v2.1.212 or later |266| `CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION` | {/* min-version: 2.1.212 */}Cap on the total number of [WebSearch](/docs/en/tools-reference#websearch-tool-behavior) calls one session can make (default: 200). When Claude reaches the cap, further WebSearch calls return a notice telling it to continue with the information it already gathered. Accepts a positive whole number with no upper bound. Anything else is ignored and the default applies, so the cap can be raised but not turned off. Requires Claude Code v2.1.212 or later |

19Match the message you see in your terminal to a section below.19Match the message you see in your terminal to a section below.

20 20 

21| Message | Section |21| Message | Section |

22| :------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------- |22| :------------------------------------------------------------------------------------------------------------------------ | :---------------------------------------------------------------------------------------------------------------------------- |

23| `API Error: 500 Internal server error` | [Server errors](#api-error-500-internal-server-error) |23| `API Error: 500 Internal server error` | [Server errors](#api-error-500-internal-server-error) |

24| `API Error: Repeated 529 Overloaded errors` | [Server errors](#api-error-repeated-529-overloaded-errors) |24| `API Error: Repeated 529 Overloaded errors` | [Server errors](#api-error-repeated-529-overloaded-errors) |

25| `Request timed out` | [Server errors](#request-timed-out), or [Network](#unable-to-connect-to-api) if the message mentions your internet connection |25| `Request timed out` | [Server errors](#request-timed-out), or [Network](#unable-to-connect-to-api) if the message mentions your internet connection |

75| `thinking.type.enabled is not supported for this model` | [Request errors](#thinking-type-enabled-is-not-supported-for-this-model) |75| `thinking.type.enabled is not supported for this model` | [Request errors](#thinking-type-enabled-is-not-supported-for-this-model) |

76| `max_tokens must be greater than thinking.budget_tokens` | [Request errors](#thinking-budget-exceeds-output-limit) |76| `max_tokens must be greater than thinking.budget_tokens` | [Request errors](#thinking-budget-exceeds-output-limit) |

77| `API Error: 400 due to tool use concurrency issues` | [Request errors](#tool-use-or-thinking-block-mismatch) |77| `API Error: 400 due to tool use concurrency issues` | [Request errors](#tool-use-or-thinking-block-mismatch) |

78| `Claude Code is unable to respond to this request, which appears to violate our Usage Policy` | [Request errors](#usage-policy-refusal) |78| `<model> can't help with this. Start a new session to continue` | [Request errors](#usage-policy-refusal) |

79| `<model> has safety measures that flagged this message for a cybersecurity topic` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |79| {/* max-version: 2.1.218 */}`Claude Code is unable to respond to this request, which appears to violate our Usage Policy` | [Request errors](#usage-policy-refusal) |

80| `<model>'s safeguards flagged this message` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |

81| {/* max-version: 2.1.218 */}`<model> has safety measures that flagged this message for a cybersecurity topic` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |

80| `Installation was killed before it could finish (exit code 137)` | [Installation errors](#installation-was-killed-before-it-could-finish) |82| `Installation was killed before it could finish (exit code 137)` | [Installation errors](#installation-was-killed-before-it-could-finish) |

81| `The connection dropped while downloading the update` | [Installation errors](#the-connection-dropped-while-downloading-the-update) |83| `The connection dropped while downloading the update` | [Installation errors](#the-connection-dropped-while-downloading-the-update) |

82| `Download timed out: exceeded the total deadline` | [Installation errors](#the-connection-dropped-while-downloading-the-update) |84| `Download timed out: exceeded the total deadline` | [Installation errors](#the-connection-dropped-while-downloading-the-update) |

1074The API declined to respond because content in the conversation triggered a [Usage Policy](https://www.anthropic.com/legal/aup) check. The message includes a Request ID you can quote to support if you believe the refusal is incorrect.1076The API declined to respond because content in the conversation triggered a [Usage Policy](https://www.anthropic.com/legal/aup) check. The message includes a Request ID you can quote to support if you believe the refusal is incorrect.

1075 1077 

1076```text theme={null}1078```text theme={null}

1077API Error: Claude Code is unable to respond to this request, which appears to violate our Usage Policy (https://www.anthropic.com/legal/aup). Please double press esc to edit your last message or start a new session for Claude Code to assist with a different task.1079API Error: Opus 4.6 can't help with this. Start a new session to continue.

1080 

1081Send feedback with /feedback or learn more: https://www.anthropic.com/legal/aup

1078```1082```

1079 1083 

1084The message names the model that declined, or `Claude` when no model is recorded. In [non-interactive mode](/docs/en/headless) (`-p`), the final line reads `Learn more:` followed by the link, without the `/feedback` mention.

1085 

1080The check evaluates the full conversation, not only your latest prompt, so sending a new message in the same session usually re-triggers the same refusal. The same applies after exiting and reopening the session with `--continue` or `--resume`, since the transcript on disk still contains the triggering content. On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), and [Microsoft Foundry](/docs/en/microsoft-foundry), this message also covers requests the model's safety measures flagged as a cybersecurity topic. See [Safety measures flagged a cybersecurity topic](#safety-measures-flagged-a-cybersecurity-topic).1086The check evaluates the full conversation, not only your latest prompt, so sending a new message in the same session usually re-triggers the same refusal. The same applies after exiting and reopening the session with `--continue` or `--resume`, since the transcript on disk still contains the triggering content. On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), and [Microsoft Foundry](/docs/en/microsoft-foundry), this message also covers requests the model's safety measures flagged as a cybersecurity topic. See [Safety measures flagged a cybersecurity topic](#safety-measures-flagged-a-cybersecurity-topic).

1081 1087 

1088{/* max-version: 2.1.218 */}Before v2.1.219, the message read `Claude Code is unable to respond to this request, which appears to violate our Usage Policy (https://www.anthropic.com/legal/aup). Please double press esc to edit your last message or start a new session for Claude Code to assist with a different task.`

1089 

1082**What to do:**1090**What to do:**

1083 1091 

1084* Press Esc twice or run `/rewind` to step back to a checkpoint before the turn that triggered the refusal, then rephrase or take a different approach. See [Checkpointing](/docs/en/checkpointing).1092* Press Esc twice or run `/rewind` to step back to a checkpoint before the turn that triggered the refusal, then rephrase or take a different approach. See [Checkpointing](/docs/en/checkpointing).

1090The model's safety measures flagged content in the conversation as a cybersecurity topic. The message names the model that flagged the request:1098The model's safety measures flagged content in the conversation as a cybersecurity topic. The message names the model that flagged the request:

1091 1099 

1092```text theme={null}1100```text theme={null}

1093API Error: Opus 4.8 has safety measures that flagged this message for a cybersecurity topic. To learn about the Cyber Verification Program and apply for access, visit our help center: https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude.1101API Error: Opus 4.8's safeguards flagged this message. Our intentionally broad safeguards allow us to deliver more capabilities faster, but can sometimes flag legitimate cybersecurity work. Apply to the Cyber Verification Program to reduce these interruptions. Send feedback with /feedback or learn more: https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude

1094 

1095If you were not engaging in a cybersecurity topic, please send feedback via /feedback.

1096```1102```

1097 1103 

1098The message links to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude), which grants access for legitimate cybersecurity work. The safeguard itself is server-side and predates v2.1.203; this release changed only the wording of the message and the page it links to.1104The message links to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude), which grants access for legitimate cybersecurity work.

1099 1105 

1100What you see depends on your provider and mode:1106What you see depends on your provider and mode:

1101 1107 

1102* On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), and [Microsoft Foundry](/docs/en/microsoft-foundry), a cybersecurity flag produces the [Usage Policy refusal](#usage-policy-refusal) message instead.1108* On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), and [Microsoft Foundry](/docs/en/microsoft-foundry), a cybersecurity flag produces the [Usage Policy refusal](#usage-policy-refusal) message instead.

1103* [Non-interactive mode](/docs/en/headless) omits the `/feedback` sentence.1109* In [non-interactive mode](/docs/en/headless), the final sentence reads `Learn more:` followed by the link, without the `/feedback` mention.

1104 1110 

1105{/* max-version: 2.1.202 */}Before v2.1.203, the message read `<model>'s safeguards flagged this message for a cybersecurity topic. If your work requires this access, you can apply for an exemption:` followed by an exemption form link.1111The safeguard itself is server-side and predates v2.1.203; client releases since then have changed only the message's wording.

1112{/* max-version: 2.1.218 */}From v2.1.203 through v2.1.218, the message read `<model> has safety measures that flagged this message for a cybersecurity topic. To learn about the Cyber Verification Program and apply for access, visit our help center:` followed by the same help-center link, and interactive sessions appended `If you were not engaging in a cybersecurity topic, please send feedback via /feedback.`

1113{/* max-version: 2.1.202 */}Before v2.1.203, it read `<model>'s safeguards flagged this message for a cybersecurity topic. If your work requires this access, you can apply for an exemption:` followed by an exemption form link.

1106 1114 

1107**What to do:**1115**What to do:**

1108 1116 

1354 1362 

1355* **Unrecognized**: the entry matches no tool name, usually a typo such as `Grpe` for `Grep`.1363* **Unrecognized**: the entry matches no tool name, usually a typo such as `Grpe` for `Grep`.

1356* **Not available to subagents**: the entry names a real tool that [subagents can't use](/docs/en/sub-agents#available-tools). Background subagents keep a smaller built-in tool set, so an entry that only a foreground subagent can use lands here when the subagent would run in the background, which is the default. If you list `Agent`, the message reports it under the next group instead.1364* **Not available to subagents**: the entry names a real tool that [subagents can't use](/docs/en/sub-agents#available-tools). Background subagents keep a smaller built-in tool set, so an entry that only a foreground subagent can use lands here when the subagent would run in the background, which is the default. If you list `Agent`, the message reports it under the next group instead.

1357* **Matched no tools in this session**: the entry is valid but no tool in the current session matches it right now, such as `mcp__github__*` with no GitHub MCP server connected, or `Agent` while [nested spawning](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents) is off.1365* **Matched no tools in this session**: the entry is valid but no tool in the current session matches it right now, such as `mcp__github__*` with no GitHub MCP server connected, or `Agent` for a subagent at the [depth limit](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents).

1358 1366 

1359Omitting the `tools` field never triggers this refusal. If you leave the `tools` list empty, or `disallowedTools` removes every entry in it, Claude Code also skips the refusal and launches the subagent without tools.1367Omitting the `tools` field never triggers this refusal. If you leave the `tools` list empty, or `disallowedTools` removes every entry in it, Claude Code also skips the refusal and launches the subagent without tools.

1360 1368 

1370* Remove entries for tools the session doesn't have, such as MCP tools from a server that isn't connected1378* Remove entries for tools the session doesn't have, such as MCP tools from a server that isn't connected

1371* For a tool that [background subagents drop](/docs/en/sub-agents#available-tools), such as `LSP` or `TaskCreate`, remove the entry or ask Claude to run the subagent in the foreground1379* For a tool that [background subagents drop](/docs/en/sub-agents#available-tools), such as `LSP` or `TaskCreate`, remove the entry or ask Claude to run the subagent in the foreground

1372* Delete the `tools` field instead of listing tools to give the subagent every [tool available to subagents](/docs/en/sub-agents#available-tools)1380* Delete the `tools` field instead of listing tools to give the subagent every [tool available to subagents](/docs/en/sub-agents#available-tools)

1373* For a `tools` list that contains only `Agent`, allow [nested spawning](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents) or give the agent at least one other tool: `Agent` isn't available inside a subagent by default, so a list with nothing else in it resolves to no tools1381* For a `tools` list that contains only `Agent`, raise the [depth limit](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents) or give the agent at least one other tool: Claude Code withholds `Agent` at that limit, so a list with nothing else in it resolves to no tools

1374 1382 

1375### File is covered by a Read deny rule1383### File is covered by a Read deny rule

1376 1384 

338| `voiceEnabled` | Legacy alias for `voice.enabled`. Prefer the `voice` object | `true` |338| `voiceEnabled` | Legacy alias for `voice.enabled`. Prefer the `voice` object | `true` |

339| `wheelScrollAccelerationEnabled` | {/* min-version: 2.1.174 */}**Default**: `true`. In [fullscreen rendering](/docs/en/fullscreen#mouse-wheel-scrolling), accelerate mouse-wheel scroll speed during fast scrolls. Set to `false` for a constant scroll rate per wheel notch. Requires Claude Code v2.1.174 or later | `false` |339| `wheelScrollAccelerationEnabled` | {/* min-version: 2.1.174 */}**Default**: `true`. In [fullscreen rendering](/docs/en/fullscreen#mouse-wheel-scrolling), accelerate mouse-wheel scroll speed during fast scrolls. Set to `false` for a constant scroll rate per wheel notch. Requires Claude Code v2.1.174 or later | `false` |

340| `workflowKeywordTriggerEnabled` | {/* min-version: 2.1.157 */}**Default**: `true`. Whether the keyword `ultracode` in a prompt you type triggers a [dynamic workflow](/docs/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. Appears in `/config` as **Ultracode keyword trigger**. Added in v2.1.157; before v2.1.160 the trigger keyword was `workflow` | `false` |340| `workflowKeywordTriggerEnabled` | {/* min-version: 2.1.157 */}**Default**: `true`. Whether the keyword `ultracode` in a prompt you type triggers a [dynamic workflow](/docs/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. Appears in `/config` as **Ultracode keyword trigger**. Added in v2.1.157; before v2.1.160 the trigger keyword was `workflow` | `false` |

341| `workflowSizeGuideline` | {/* min-version: 2.1.219 */}**Default**: `medium`. Sets the [agent count Claude aims for](/docs/en/workflows#set-a-size-guideline) in the dynamic workflows it writes. Claude Code sends the value to Claude as advice, not an enforced cap. Accepts `unrestricted`, `small`, `medium`, or `large`. Takes precedence over the **Dynamic workflow size** choice in `/config`, and Claude Code hides that row while a settings file sets the key. Requires Claude Code v2.1.219 or later; {/* min-version: 2.1.202 */}on v2.1.202 through v2.1.218, set the guideline in `/config` instead | `"small"` |

341| `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` |342| `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` |

342 343 

343### Global config settings344### Global config settings

349</Note>350</Note>

350 351 

351| Key | Description | Example |352| Key | Description | Example |

352| :--------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------- |353| :--------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------- |

353| `autoConnectIde` | **Default**: `false`. Automatically connect to a running IDE when Claude Code starts from an external terminal. Appears in `/config` as **Auto-connect to IDE (external terminal)** when running outside a VS Code or JetBrains terminal. The [`CLAUDE_CODE_AUTO_CONNECT_IDE`](/docs/en/env-vars) environment variable overrides this when set | `true` |354| `autoConnectIde` | **Default**: `false`. Automatically connect to a running IDE when Claude Code starts from an external terminal. Appears in `/config` as **Auto-connect to IDE (external terminal)** when running outside a VS Code or JetBrains terminal. The [`CLAUDE_CODE_AUTO_CONNECT_IDE`](/docs/en/env-vars) environment variable overrides this when set | `true` |

354| `autoInstallIdeExtension` | **Default**: `true`. Automatically install the Claude Code IDE extension when running from a VS Code terminal. Appears in `/config` as **Auto-install IDE extension** when running inside a VS Code or JetBrains terminal. You can also set the [`CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL`](/docs/en/env-vars) environment variable to `1` | `false` |355| `autoInstallIdeExtension` | **Default**: `true`. Automatically install the Claude Code IDE extension when running from a VS Code terminal. Appears in `/config` as **Auto-install IDE extension** when running inside a VS Code or JetBrains terminal. You can also set the [`CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL`](/docs/en/env-vars) environment variable to `1` | `false` |

355| `diffTool` | **Default**: `auto`. Where to display file diffs when an IDE is connected: `auto` opens diffs in the IDE's diff viewer, `terminal` keeps them in the terminal. Appears in `/config` as **Diff tool** only when Claude Code is connected to a VS Code or JetBrains IDE | `"terminal"` |356| `diffTool` | **Default**: `auto`. Where to display file diffs when an IDE is connected: `auto` opens diffs in the IDE's diff viewer, `terminal` keeps them in the terminal. Appears in `/config` as **Diff tool** only when Claude Code is connected to a VS Code or JetBrains IDE | `"terminal"` |

356| `externalEditorContext` | **Default**: `false`. Prepend Claude's previous response as `#`-commented context when you open the external editor with `Ctrl+G`. Appears in `/config` as **Show last response in external editor** | `true` |357| `externalEditorContext` | **Default**: `false`. Prepend Claude's previous response as `#`-commented context when you open the external editor with `Ctrl+G`. Appears in `/config` as **Show last response in external editor** | `true` |

357| `permissionExplainerEnabled` | **Default**: `true`. Show a model-generated [explanation of the command](/docs/en/permissions#permission-system) when you press `Ctrl+E` on a Bash or PowerShell permission prompt. Set to `false` to turn the shortcut off | `false` |358| `permissionExplainerEnabled` | **Default**: `true`. Show a model-generated [explanation of the command](/docs/en/permissions#permission-system) when you press `Ctrl+E` on a Bash or PowerShell permission prompt. Set to `false` to turn the shortcut off | `false` |

358| `teammateDefaultModel` | Default model for [agent team](/docs/en/agent-teams) teammates when the spawn prompt doesn't specify one. Set to a model alias such as `"sonnet"`, or `null` to inherit the lead's current `/model` selection. Appears in `/config` as **Default teammate model** | `"sonnet"` |359| `teammateDefaultModel` | Default model for [agent team](/docs/en/agent-teams) teammates when the spawn prompt doesn't specify one. Set to a model alias such as `"sonnet"`, or `null` to inherit the lead's current `/model` selection. Appears in `/config` as **Default teammate model** | `"sonnet"` |

359| `workflowSizeGuideline` | {/* min-version: 2.1.202 */}**Default**: `unrestricted`, which sends no guideline. Sets the [agent count Claude aims for](/docs/en/workflows#set-a-size-guideline) in the dynamic workflows it writes. Claude Code sends the value to Claude as advice, not an enforced cap. Accepts `unrestricted`, `small`, `medium`, or `large`. Appears in `/config` as **Dynamic workflow size**. You can also set it directly with `/config workflowSizeGuideline=small`. Requires Claude Code v2.1.202 or later. {/* min-version: 2.1.203 */}The guideline's agent count also replaces the default threshold for the [`Large workflow` warning](/docs/en/workflows#cost); that behavior requires Claude Code v2.1.203 or later | `"small"` |

360 360 

361### Worktree settings361### Worktree settings

362 362 

323 323 

324Subagents inherit the [built-in tools](/docs/en/tools-reference) and MCP tools available in the main conversation, narrowed by two filters: the first removes a short list of tools from every subagent, and the second reduces the built-in tool set for subagents that run in the [background](#run-subagents-in-foreground-or-background), which is the default. [Forks](#fork-the-current-conversation) skip both filters and receive the main conversation's exact tool pool. The first filter removes these tools, even when listed in the `tools` field:324Subagents inherit the [built-in tools](/docs/en/tools-reference) and MCP tools available in the main conversation, narrowed by two filters: the first removes a short list of tools from every subagent, and the second reduces the built-in tool set for subagents that run in the [background](#run-subagents-in-foreground-or-background), which is the default. [Forks](#fork-the-current-conversation) skip both filters and receive the main conversation's exact tool pool. The first filter removes these tools, even when listed in the `tools` field:

325 325 

326* `Agent`, until you turn on [nested spawning](#let-subagents-spawn-their-own-subagents); in a [fork](#fork-the-current-conversation) the tool stays listed but returns an error instead of spawning326* `Agent`, when the subagent is at the [depth limit](#let-subagents-spawn-their-own-subagents); in a [fork](#fork-the-current-conversation) the tool stays listed but returns an error instead of spawning

327* `AskUserQuestion`327* `AskUserQuestion`

328* `EndConversation`, which can end only the main conversation; see [EndConversation tool behavior](/docs/en/tools-reference#endconversation-tool-behavior)328* `EndConversation`, which can end only the main conversation; see [EndConversation tool behavior](/docs/en/tools-reference#endconversation-tool-behavior)

329* `EnterPlanMode`329* `EnterPlanMode`

395 395 

396If you omit `Agent` from the `tools` list entirely, the agent can't spawn any subagents with the Agent tool.396If you omit `Agent` from the `tools` list entirely, the agent can't spawn any subagents with the Agent tool.

397 397 

398The `Agent(agent_type)` allowlist syntax applies only to an agent running as the main thread with `claude --agent`. In a subagent definition, listing `Agent` in `tools` lets that subagent spawn subagents of its own once you allow [nested spawning](#let-subagents-spawn-their-own-subagents), but any type list inside the parentheses is ignored.398The `Agent(agent_type)` allowlist syntax applies only to an agent running as the main thread with `claude --agent`. In a subagent definition, listing `Agent` in `tools` lets that subagent spawn subagents of its own while the [depth limit](#let-subagents-spawn-their-own-subagents) allows it, but any type list inside the parentheses is ignored.

399 399 

400#### Scope MCP servers to a subagent400#### Scope MCP servers to a subagent

401 401 

845 845 

846### Let subagents spawn their own subagents846### Let subagents spawn their own subagents

847 847 

848By default, a subagent can't spawn subagents of its own, so a subagent you ask to delegate does the work itself and returns one summary. While nesting is off, Claude Code withholds the `Agent` tool from every subagent except a [fork](#fork-the-current-conversation), which inherits the parent's full tool list. `Agent` stays in that list, but returns an error instead of spawning.848By default, a subagent can spawn subagents of its own, up to three layers below the main conversation. At the depth limit, Claude Code withholds the `Agent` tool from every subagent except a [fork](#fork-the-current-conversation), so a subagent at the limit does its delegated work itself and returns one summary. A fork at the limit keeps `Agent` in its inherited tool list, but the tool returns an error instead of spawning.

849 849 

850Nested subagents suit a delegated task that itself splits into parallel subtasks, such as a reviewer subagent that dispatches a verifier per finding, so the intermediate output never reaches your main conversation. Only the top-level subagent's summary returns to you.850Nested subagents suit a delegated task that itself splits into parallel subtasks, such as a reviewer subagent that dispatches a verifier per finding, so the intermediate output never reaches your main conversation. Only the top-level subagent's summary returns to you.

851 851 

852To allow nesting, set [`CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH`](/docs/en/env-vars) to the number of subagent layers you want below your main conversation. For example, this entry in [`settings.json`](/docs/en/settings) allows two layers:852{/* min-version: 2.1.217 */}To change the limit, set [`CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH`](/docs/en/env-vars) to the number of subagent layers you want below your main conversation. For example, this entry in [`settings.json`](/docs/en/settings) caps nesting at two layers:

853 853 

854```json theme={null}854```json theme={null}

855{855{

859}859}

860```860```

861 861 

862With this value, your subagents can delegate to a second layer of their own, and that second layer can't delegate further.862With this value, your subagents can delegate to a second layer of their own, and that second layer can't delegate further. Set `1` to turn nesting off.

863 863 

864A nested subagent is configured the same way as a top-level one and resolves from the same [scopes](#choose-the-subagent-scope). To keep one subagent from spawning while nesting is on, such as a reviewer that should stay read-only, omit `Agent` from its [`tools`](#available-tools) list or add it to `disallowedTools`.864A nested subagent is configured the same way as a top-level one and resolves from the same [scopes](#choose-the-subagent-scope). To keep one subagent from spawning while nesting is on, such as a reviewer that should stay read-only, omit `Agent` from its [`tools`](#available-tools) list or add it to `disallowedTools`.

865 865 

866The subagent panel below the prompt input shows the full tree: each row displays a `(+N)` count of descendants, and {/* min-version: 2.1.193 */}as of v2.1.193, opening a row shows that subagent's siblings and direct children with a path back to `main`.866The subagent panel below the prompt input shows the full tree: each row displays a `(+N)` count of descendants, and {/* min-version: 2.1.193 */}as of v2.1.193, opening a row shows that subagent's siblings and direct children with a path back to `main`.

867 867 

868<Note>868<Note>

869 From Claude Code v2.1.172 through v2.1.216, subagents could nest by default, up to five layers deep, and the limit couldn't be changed.869 Earlier versions used different defaults:

870 

871 * **v2.1.172 through v2.1.216**: subagents could nest by default, up to five layers deep, and the limit couldn't be changed.

872 * **v2.1.217 through v2.1.218**: the limit defaulted to one, so a subagent couldn't spawn its own unless you raised it; {/* min-version: 2.1.219 */}v2.1.219 raised the default to three.

870</Note>873</Note>

871 874 

872### Session subagent limit875### Session subagent limit

645 645 

646If your Git is installed somewhere else, find the path by running `where.exe git` in PowerShell and use the `bin\bash.exe` path from that directory.646If your Git is installed somewhere else, find the path by running `where.exe git` in PowerShell and use the `bin\bash.exe` path from that directory.

647 647 

648**If the path is correct and the file exists** but Claude Code still reports it as not found, endpoint security software such as AppLocker, Group Policy software restriction policies, or EDR agents may be interfering. On versions before v2.1.116, Claude Code spawned a child process (`cmd.exe`) to verify the path, which these policies can block — a common signal is that `cmd.exe /c dir "C:\Program Files\Git\bin\bash.exe"` works when you run it directly in PowerShell but fails silently when launched by `claude.exe`.648**If the path is correct and the file exists** but Claude Code still doesn't use it, check the file's name first. {/* min-version: 2.1.219 */}Claude Code accepts only a file named `bash.exe`, `sh.exe`, `bash`, or `sh`; with any other name, such as Git for Windows' `git-bash.exe` launcher, it ignores the variable and auto-detects Git Bash as if it were unset, logging a warning visible with `--debug`. A path that doesn't exist gets the same fallback and warning. Before v2.1.219, Claude Code used any existing file as the shell without checking its name, and exited at startup with `Claude Code was unable to find CLAUDE_CODE_GIT_BASH_PATH path` when the path didn't exist.

649 

650If the file's name is right, endpoint security software such as AppLocker, Group Policy software restriction policies, or EDR agents may be interfering. On versions before v2.1.116, Claude Code spawned a `cmd.exe` child process to verify the path, which these policies can block. A common signal is that `cmd.exe /c dir "C:\Program Files\Git\bin\bash.exe"` works when you run it directly in PowerShell but fails silently when launched by `claude.exe`.

649 651 

650Claude Code v2.1.116 and later check the filesystem directly, so update first. If the error persists on a current version, ask your IT team to allowlist `claude.exe` and the processes it spawns, including `cmd.exe` and `bash.exe`, in your endpoint protection policy.652Claude Code v2.1.116 and later check the filesystem directly, so update first. If the error persists on a current version, ask your IT team to allowlist `claude.exe` and the processes it spawns, including `cmd.exe` and `bash.exe`, in your endpoint protection policy.

651 653 

334 334 

335A workflow spawns many agents, so a single run can use meaningfully more tokens than working through the same task in conversation. Runs count toward your plan's usage and rate limits like any other session.335A workflow spawns many agents, so a single run can use meaningfully more tokens than working through the same task in conversation. Runs count toward your plan's usage and rate limits like any other session.

336 336 

337To gauge the spend before committing to a large task, run the workflow on a small slice first: one directory instead of the whole repo, or a narrow question instead of a broad one. The `/workflows` view shows each agent's token usage as the run progresses, and you can stop the run there at any time without losing completed work. The runtime's [agent caps](#behavior-and-limits) limit how many agents a single run can spawn, which bounds the cost of a runaway script. To keep every run smaller by default, [set a size guideline](#set-a-size-guideline) in `/config`.337To gauge the spend before committing to a large task, run the workflow on a small slice first: one directory instead of the whole repo, or a narrow question instead of a broad one. The `/workflows` view shows each agent's token usage as the run progresses, and you can stop the run there at any time without losing completed work. The runtime's [agent caps](#behavior-and-limits) limit how many agents a single run can spawn, which bounds the cost of a runaway script. To keep runs to fewer agents, choose the `small` [size guideline](#set-a-size-guideline).

338 338 

339Claude Code also flags a run that grows unusually large. When a workflow schedules more than 25 agents, or its projected token total passes 1.5 million, its progress line in the task panel below the input box shows a `Large workflow` warning. The warning points you to [`/workflows`](#watch-the-run), where you can stop the run. Requires Claude Code v2.1.203 or later.339Claude Code also flags a run that grows unusually large. When a workflow schedules more than 25 agents, or its projected token total passes 1.5 million, its progress line in the task panel below the input box shows a `Large workflow` warning. The warning points you to [`/workflows`](#watch-the-run), where you can stop the run. Requires Claude Code v2.1.203 or later.

340 340 

341The warning is advisory: it doesn't pause or limit the run. Two settings change when you see it:341The warning is advisory: it doesn't pause or limit the run. Two settings change when you see it:

342 342 

343* If you [set a size guideline](#set-a-size-guideline), the guideline's agent count replaces the 25-agent threshold.343* If you choose a [size guideline](#set-a-size-guideline) yourself, its agent count replaces the 25-agent threshold. The built-in default guideline leaves the threshold at 25.

344* Sessions with [ultracode](#let-claude-decide-with-ultracode) on don't show the warning, because turning ultracode on already opts you in to large runs.344* Sessions with [ultracode](#let-claude-decide-with-ultracode) on don't show the warning, because turning ultracode on already opts you in to large runs.

345 345 

346Every agent in a workflow uses your session's model unless the script routes a stage to a different one or the [`CLAUDE_CODE_SUBAGENT_MODEL`](/docs/en/model-config#environment-variables) environment variable is set, which overrides both. To control the model cost:346Every agent in a workflow uses your session's model unless the script routes a stage to a different one or the [`CLAUDE_CODE_SUBAGENT_MODEL`](/docs/en/model-config#environment-variables) environment variable is set, which overrides both. To control the model cost:

350 350 

351### Set a size guideline351### Set a size guideline

352 352 

353The Dynamic workflow size setting in `/config` keeps the workflows Claude writes to a smaller scale by default. Claude Code sends the setting to Claude as advice, so a prompt that calls for a different scale still overrides it. Requires Claude Code v2.1.202 or later.353A size guideline tells Claude how many agents to aim for when it writes a dynamic workflow. Claude Code sends the guideline to Claude as advice, not a cap, so a prompt that calls for a different scale still overrides it. Requires Claude Code v2.1.202 or later.

354 354 

355Each value sets the agent count Claude aims for in the scripts it writes.355Each value maps to an agent count:

356 356 

357| Value | Guidance sent to Claude |357| Value | Agent count Claude aims for |

358| :------------- | :--------------------------------- |358| :------------- | :-------------------------------------------------- |

359| `unrestricted` | No guideline. This is the default. |359| `unrestricted` | No guideline: Claude sizes the workflow to the task |

360| `small` | Aim for fewer than 5 agents. |360| `small` | Fewer than 5 agents |

361| `medium` | Aim for fewer than 15 agents. |361| `medium` | Fewer than 15 agents |

362| `large` | Aim for fewer than 50 agents. |362| `large` | Fewer than 50 agents |

363 

364{/* min-version: 2.1.219 */}The default is `medium`. Until you choose a value, the `/config` row shows `medium (default)` and the workflow's `Running in background` line shows `medium size (/config)`. Requires Claude Code v2.1.219 or later; earlier versions default to `unrestricted`.

365 

366To change the guideline, pick a value for the Dynamic workflow size setting in `/config`, or run `/config workflowSizeGuideline=small`. {/* min-version: 2.1.219 */}On v2.1.219 and later, you can also set the [`workflowSizeGuideline` key](/docs/en/settings#available-settings) in any settings file; that value takes precedence over `/config`, and Claude Code hides the `/config` row while a settings file provides one.

363 367 

364Changes take effect on the next prompt. The [runtime agent caps](#behavior-and-limits) still apply regardless of the setting.368Changes take effect on the next prompt. The [runtime agent caps](#behavior-and-limits) still apply regardless of the setting.

365 369