claude-code-20260901T180701Z / documentation capture

What this read moved

1–22 of 22

advisor Changed · +23 / -23 lines

from line 28

2828

2929Each of these enables the advisor for sessions whose main model [supports it](#choose-an-advisor-model). After the session starts, Claude Code shows an `Advisor Tool (experimental) is on and may use more tokens · /advisor` notification. To stop using the advisor, see [Turn the advisor off](#turn-the-advisor-off).

3030

31On some plans, Fable as the advisor also needs your one-time [consent to bill Fable 5 usage to usage credits](/docs/en/model-config#fable-5-and-usage-credits). For what happens before you have given that consent, see [Fable advisor and usage credits](#fable-advisor-and-usage-credits).

31On some plans, Fable as the advisor also needs your one-time [consent to bill Fable usage to usage credits](/docs/en/model-config#fable-and-usage-credits). For what happens before you have given that consent, see [Fable advisor and usage credits](#fable-advisor-and-usage-credits).

3232

3333### Use the `/advisor` command

3434

from line 42

4242

4343Claude Code doesn't invoke a saved advisor that your organization's [`availableModels`](/docs/en/model-config#restrict-model-selection) allowlist excludes. To use the advisor, pick an allowed model with `/advisor`. Claude Code still saves an advisor that your current main model doesn't support. That advisor activates after you switch to a [compatible main model](#choose-an-advisor-model) with [`/model`](/docs/en/model-config#setting-your-model).

4444

45On some plans, Fable as the advisor also needs your one-time [consent to bill Fable 5 usage to usage credits](/docs/en/model-config#fable-5-and-usage-credits). For what `/advisor fable` does before you have given that consent, see [Fable advisor and usage credits](#fable-advisor-and-usage-credits).

45On some plans, Fable as the advisor also needs your one-time [consent to bill Fable usage to usage credits](/docs/en/model-config#fable-and-usage-credits). For what `/advisor fable` does before you have given that consent, see [Fable advisor and usage credits](#fable-advisor-and-usage-credits).

4646

4747### Set `advisorModel` in settings

4848

from line 75

7575

7676The advisor must be at least as capable as the main model. The accepted advisors for each main model are:

7777

78| Main model | Accepted advisors | Notes |

79| ------------------- | ---------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

80| Haiku 4.5 | Fable, Opus, Sonnet | Haiku can call the advisor but cannot act as one |

81| Sonnet 4.6 | Fable, Opus, Sonnet | |

82| Sonnet 5 | Fable, Opus, Sonnet 5 | A Sonnet 4.6 advisor is rejected |

83| Opus 4.6 | Fable, Opus, Sonnet 5 | Sonnet 5 and Opus 4.6 are ranked as equally capable, so an Opus 4.6 main accepts a Sonnet 5 advisor |

84| Opus 4.7 or later | Fable, and Opus 4.7 or later | Opus 4.7 and later Opus models are ranked as equally capable, so any of them accepts another as an advisor. An Opus 4.7 main with an Opus 4.6 or Sonnet 5 advisor is rejected |

85| Fable 5 (v2.1.170+) | Fable | An Opus or Sonnet advisor is rejected |

78| Main model | Accepted advisors | Notes |

79| -------------------- | ------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

80| Haiku 4.5 | Fable, Opus, Sonnet | Haiku can call the advisor but cannot act as one |

81| Sonnet 4.6 | Fable, Opus, Sonnet | |

82| Sonnet 5 | Fable, Opus, Sonnet 5 | A Sonnet 4.6 advisor is rejected |

83| Opus 4.6 | Fable, Opus, Sonnet 5 | Sonnet 5 and Opus 4.6 are ranked as equally capable, so an Opus 4.6 main accepts a Sonnet 5 advisor |

85| Fable 5.1 or Fable 5 | Fable 5.1, or the same Fable version | An Opus or Sonnet advisor is rejected, and so is a Fable 5 advisor for a Fable 5.1 main model |

8686

87Fable 5 requires Claude Code v2.1.170 or later and [Fable 5 access](/docs/en/model-config#work-with-fable-5), whether it acts as the main model or the advisor.

87Fable 5.1 requires Claude Code v2.1.255 or later and Fable 5 requires v2.1.170 or later, plus [Fable access](/docs/en/model-config#work-with-fable).

8888

8989Set the advisor as `fable`, `opus`, or `sonnet`. These aliases resolve to Claude Code's built-in default version for each model family, which advances with new Claude Code releases. You can also pass a full model ID such as `claude-opus-5`.

9090

from line 97

9797

9898### Fable advisor and usage credits

9999

100On some plans, Fable 5 usage bills to usage credits, and Claude Code asks for your [one-time consent to bill Fable 5 usage to usage credits](/docs/en/model-config#fable-5-and-usage-credits) when you select Fable 5 with `/model`. Fable as the advisor bills the same way, so on those plans Claude Code doesn't apply Fable as the advisor until you have accepted that consent.

100On some plans, Fable usage bills to usage credits, and Fable as the advisor bills the same way. If your account requires the [one-time consent to bill Fable usage to usage credits](/docs/en/model-config#fable-and-usage-credits), Claude Code asks for it when you select a Fable model with `/model` and doesn't apply Fable as the advisor until you have accepted that consent.

101101

102102Before you have accepted it, Claude Code doesn't save Fable as the advisor when you type `/advisor fable` or pick Fable in the `/advisor` picker. It points you to `/model fable` instead. With `claude --advisor fable`, Claude Code exits at launch with a message that points to `/model fable`. In a [background session](#use-the-advisor-flag), it starts the session without the advisor instead of exiting. With Fable already saved as your `advisorModel`, Claude Code sends requests without the advisor. In an interactive session whose main model supports the advisor, it also shows a notification that points to `/model fable`.

103103

104To accept the consent, run `/model fable` and choose to continue on Fable 5. Claude Code records the consent and [saves Fable 5 as your selected model](/docs/en/model-config#default-model-setting). Then select Fable as the advisor.

104To accept the consent, run `/model fable` and choose to continue on Fable. Claude Code records the consent and [saves Fable as your selected model](/docs/en/model-config#default-model-setting). Then select Fable as the advisor.

105105

106106### Common model pairings

107107

108108Any accepted pairing works. These combinations balance cost against capability in different ways:

109109

110| Pairing | When to use |

111| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

112| Sonnet main + Opus advisor | Sonnet handles routine work and escalates planning, ambiguous failures, and completion checks to Opus |

113| Sonnet main + Fable advisor | Fable 5 guidance at decision points without running Fable 5 throughout. Requires v2.1.170 or later and Fable 5 access |

114| Haiku main + Opus advisor | Lowest-cost main model with strong planning. Expect higher cost than Haiku alone but lower than switching the main model to Sonnet or Opus |

115| Opus main + Opus advisor | A second Opus reviews the first. Useful for high-stakes tasks where an independent check matters more than cost |

116| Fable main + Fable advisor | Highest-capability pairing when Fable 5 is available (v2.1.170+). Fable is a higher tier than Opus and Sonnet, so it is the only accepted advisor for a Fable main model |

117| Sonnet main + Sonnet advisor | A lower-cost second opinion for catching routine oversights |

110| Pairing | When to use |

111| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |

112| Sonnet main + Opus advisor | Sonnet handles routine work and escalates planning, ambiguous failures, and completion checks to Opus |

113| Sonnet main + Fable advisor | Fable guidance at decision points without running Fable throughout. Requires Fable access |

114| Haiku main + Opus advisor | Lowest-cost main model with strong planning. Expect higher cost than Haiku alone but lower than switching the main model to Sonnet or Opus |

115| Opus main + Opus advisor | A second Opus reviews the first. Useful for high-stakes tasks where an independent check matters more than cost |

116| Fable main + Fable advisor | Highest-capability pairing when Fable is available. Claude Code doesn't apply an Opus or Sonnet advisor to a Fable main model |

117| Sonnet main + Sonnet advisor | A lower-cost second opinion for catching routine oversights |

118118

119119## When Claude consults the advisor

120120

from line 135

135135

136136## Cost

137137

138When Claude calls the advisor, the advisor model reads the conversation, so each call consumes tokens at the advisor model's rates in addition to your main model's usage. With API billing, you pay the advisor model's input and output rates for advisor tokens. On subscription plans, advisor usage counts toward your plan's usage limits, except that a Fable 5 advisor bills to [usage credits](/docs/en/model-config#fable-5-and-usage-credits) on plans where Fable 5 usage does. If your account requires the usage-credits consent, a Fable advisor bills nothing before you give it, because Claude Code [doesn't apply the selection](#fable-advisor-and-usage-credits) until then.

138When Claude calls the advisor, the advisor model reads the conversation, so each call consumes tokens at the advisor model's rates in addition to your main model's usage. With API billing, you pay the advisor model's input and output rates for advisor tokens. On subscription plans, advisor usage counts toward your plan's usage limits, except that a Fable advisor bills to [usage credits](/docs/en/model-config#fable-and-usage-credits) on plans where Fable usage does. If your account requires the usage-credits consent, a Fable advisor bills nothing before you give it, because Claude Code [doesn't apply the selection](#fable-advisor-and-usage-credits) until then.

139139

140140Claude calls the advisor at decision points rather than on every turn, so pairing a faster main model with a stronger advisor typically costs less than running the stronger model throughout. Advisor usage counts toward the session totals shown by [`/usage`](/docs/en/costs#track-your-costs).

141141

from line 152

152152The advisor tool requires all of the following:

153153

154154* **Anthropic API only**: the advisor is a server-executed tool. It is not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry. Through an [LLM gateway](/docs/en/llm-gateway) configured with `ANTHROPIC_BASE_URL`, availability depends on whether the gateway forwards the request intact to the Anthropic API.

155* **Supported main model**: Opus 4.6 or later, Sonnet 4.6 or later, or Haiku 4.5. Fable 5 also qualifies on Claude Code v2.1.170 or later, and a Fable 5 main [accepts only a Fable advisor](#choose-an-advisor-model).

155* **Supported main model**: Fable, Opus 4.6 or later, Sonnet 4.6 or later, or Haiku 4.5. See [Choose an advisor model](#choose-an-advisor-model) for which advisors each accepts.

156156* **Feature-flag fetching**: Claude Code turns the advisor on through a feature flag it fetches from Anthropic. In a session where a variable that turns flag fetching off is set, such as `DISABLE_TELEMETRY`, the advisor stays off. See [Features that need feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching).

157157

158158## Turn the advisor off

changelog Changed · +107 / -0 lines

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

from line 6

77Run `claude --version` to check your installed version.

9<Update label="2.1.257" description="September 1, 2026">

10 * Added Claude Fable 5.1 (`claude-fable-5-1`), now the default Fable model — 1M context, $10/$50 per Mtok with \$0.25/Mtok cache reads

11 * Added "Time format" (`timeFormat`) and `timeZone` settings: 12-hour, 24-hour, 24-hour UTC, or a strftime pattern for the turn-end clock and transcript-view timestamps

12 * Added a Containment Escape rule to auto mode so cloud metadata-credential fetches, egress evasion, and cross-tenant reach are no longer auto-approved unless your environment marks them expected

13 * Added `CLAUDE_CODE_SUBAGENT_MODEL_FORCE` to apply `CLAUDE_CODE_SUBAGENT_MODEL` (or the main model) to every subagent, ignoring per-spawn and agent-definition model overrides

14 * Added `s` in `/effort` to change effort for the current session only, matching `/model`

15 * Added a `/doctor` warning for stale sandbox mask files left by a killed session

16 * Added a one-time prompt in auto mode before the first file read outside the working directories, with the option to block such reads (`permissions.blockReadsOutsideWorkingDirectories`)

17 * Added support for a gateway-supplied `description` on discovered `/model` picker entries (`CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY`); entries without one still read "From gateway"

18 * Fixed settings in a `.claude/` folder created after startup not being picked up until restart

19 * Fixed sessions dispatched from an agent view opened with `←` always starting in the original session's permission mode, overriding the target directory's `defaultMode` and the agent's `permissionMode`

20 * Fixed `keybindings.json` rebinds of Ctrl+G being ignored in `claude agents`; its Ctrl+S / Ctrl+T are now rebindable via the new `Agents` context

21 * Fixed background sessions failing to start on macOS npm installs during a self-update, and on Windows when a stale daemon lock file pointed at a reused process id

22 * Fixed the working spinner stopping while a response streams behind a slash-command panel

23 * Fixed a background session's `state.json` `detail` repeating its own dispatch prompt after a scheduled wake-up

24 * Fixed `claude agents` keeping a background session you re-prompted buried in Completed after it finished again; Completed now orders by the latest finish

25 * Fixed `claude --bg` from a directory that was just deleted reporting "backgrounded" and leaving a crashed session row; it now prints the reason and exits 1

26 * Fixed Remote Control connecting mid-session re-sending the Bash tool definition, causing a prompt-cache miss

27 * Fixed a doubly-listed custom `Authorization` header overriding the configured credential on Bedrock, Mantle, Vertex, and WIF, and the Vertex setup wizard picking up a leftover Anthropic profile from `~/.config/anthropic`

28 * Fixed Claude apps gateway sending stray host `Authorization` or profile headers to Foundry, Vertex, and Bedrock, and Foundry Entra ID upstreams not starting when `ANTHROPIC_FOUNDRY_API_KEY` is set

29 * Fixed a leftover Anthropic API key or auth token being sent alongside your Foundry subscription key in API-key mode

30 * Fixed `/schedule` routines whose prompt was saved without a message role and then ran with nothing to do

31 * Fixed `claude agents` not saying that a background session is waiting for you to approve a message from another session, or who sent it

32 * Fixed a prompt stashed with Ctrl+S inside an opened background session being lost when the session went idle or was stopped and then reopened

33 * Fixed telemetry (OTEL) settings pushed through server-managed settings being ignored on warm starts, including desktop-app Code sessions

34 * Fixed a teammate permission request being answered twice when the leader's mailbox write was briefly locked

35 * Fixed a phantom duplicate slash-command row rendering below the in-flight turn while a command's auto-continued response streamed

36 * Fixed `policyHelper` `timeoutMs` and `refreshIntervalMs` values above the timer maximum (2147483647) causing failures or re-runs every millisecond; they are now clamped

37 * Fixed the token counter freezing or crawling after switching to another subagent's transcript, and made background subagents' and teammates' counters update live while a response streams

38 * Fixed sandbox network hosts written with a trailing dot (`example.com.`): a `deniedDomains` entry didn't block the host inside the sandbox, and "don't ask again" for such a host kept prompting

39 * Fixed dismissing the Remote Control consent prompt (Esc, or `n` at `claude remote-control`) counting as consent, so the next request connected without asking

40 * Fixed `/mcp` reconnect and enable still connecting a settings-file MCP server that a managed MCP allow/deny list or `strictPluginOnlyCustomization` loaded after startup should block

41 * Fixed `claude mcp remove` leaving a remote server's stored OAuth credentials behind when `strictPluginOnlyCustomization` locks MCP to plugin-only servers

42 * Fixed Remote Control (`claude remote-control`) sessions started from the Claude app ignoring the selected model and running on the machine's default instead

43 * Fixed `--disallowedTools` and session deny rules being dropped after the first settings reload when `allowManagedPermissionRulesOnly` is enabled

44 * Fixed `--resume` listing a backgrounded conversation twice and `--continue` reopening its stalled pre-background copy; `--continue` now also opens finished background sessions

45 * Fixed fullscreen mode not letting you click `!` shell command output to expand it

46 * Fixed background sessions left running an older Claude Code binary piling up across auto-updates instead of being retired

47 * Fixed `claude agents --json` briefly switching the terminal to raw mode and undoing another program's terminal settings on exit

48 * Fixed Proactive output style sessions busy-looping with filler messages and repeated log reads instead of idling while a background command or Monitor they started is still running

49 * Fixed subagents stopping when a response was cut off mid-stream by a computer sleep, dropped connection, or server error; they now automatically continue instead of ending with an incomplete response

50 * Fixed `←` doing nothing in the `/btw` panel inside a `claude agents` session: it now returns to the agents list (even mid-answer), and the panel comes back when you reopen the session

51 * Fixed sessions with an advisor model set missing the prompt cache on background requests (compaction, `/recap`, prompt suggestions) and re-sending the full conversation uncached each time

52 * Fixed `claude -p` exiting about 5 seconds after its final result while a Monitor the model armed was still running; it now waits for the watch to fire or time out

53 * Fixed a `permissions.ask` rule being skipped in auto mode when the matching command ran inside a compound command or subshell, letting it run without the confirmation prompt

54 * Fixed plugins being able to read files outside their own directory through a declared command, agent, skill, hooks or other component path that is a symlink; such paths are now refused with an error

55 * Fixed `/add-dir` rejecting a directory inside the current working directory; it now loads that directory's skills, commands, and agents like `--add-dir` does at startup

56 * Fixed the main agent not being told when you resume a subagent you had stopped from its transcript view

57 * Fixed a crash when pasting ANSI-colored text (e.g. a CI log) into dialogs like `/feedback`

58 * Fixed `claude mcp add/remove` hanging or exhausting memory when the project's `.mcp.json` is a FIFO or a device-file symlink; it now fails fast with an actionable message

59 * Fixed unbounded memory growth when non-JSONL data is piped into `claude -p --input-format stream-json`; it now fails fast with a clear error

60 * Fixed backgrounding a turn (`←` or Ctrl+B) while a subagent or other tool was running occasionally making the background session treat that tool as rejected instead of re-running it

61 * Fixed Bash `Read()`/`Edit()` deny rules not applying to `< file` redirects and reader commands like `tac` and `egrep`; a deny rule on any argument or redirect target now refuses the command

62 * Fixed resuming or messaging a subagent whose transcript had grown past 5 MB (for example after reading many images) failing with "No transcript found"

63 * Fixed worktree-isolated sessions refusing Bash loops, `$VAR` reads, `"$(…)"` and heredocs that never touch git as "too complex to verify that it stays inside the worktree"

64 * Fixed `/model` and `/effort` showing a prompt-cache warning after rewinding a conversation back to empty

65 * Fixed prompt-cache misses on every turn in long screenshot-heavy sessions once images exceeded the per-request size cap

66 * Fixed the Edit permission prompt's diff view rendering emoji and multi-code-point characters with incorrect widths

67 * Fixed WebSocket MCP server connection failures being logged as "\[object ErrorEvent]" instead of the underlying error

68 * Fixed background sessions failing to open with "Couldn't start the background service" while another Claude Code process was downloading an npm update; the start now waits for it

69 * Fixed background commands that detach from their shell (for example under `timeout` or `setsid`) surviving a task stop or Claude Code exit

70 * Fixed Claude not being told when you stop a background command from the tasks panel or a connected client

71 * Fixed stopping a background subagent leaving its monitors running

72 * Fixed sandboxed git commands in a linked worktree losing write access to the repository's common `.git` directory after `cd` into a subdirectory

73 * Fixed Bedrock and Bedrock Mantle requests going silent during long hidden-thinking phases on Opus 4.7 and later, which let idle timeouts cut the connection; the stream now carries progress events

74 * Fixed launching Claude Code after a Claude apps gateway expired or revoked your session: it now says the session ended and offers `/login` instead of reporting a network error

75 * Fixed cloud sessions losing git/GitHub credentials for the rest of the session when the session's network proxy failed to start at launch; it now retries in the background and recovers

76 * Fixed leftover `cc-daemon-*` folders in the system temp directory after an interrupted background daemon start; the `cleanupPeriodDays` retention sweep now removes them

77 * Fixed Bash permission checks auto-approving certain `[[ ]]` conditionals that zsh parses differently from bash; these commands now prompt for approval

78 * Fixed the managed-settings approval prompt showing the generic warning instead of its telemetry wording when the settings also turn detailed tracing or raw API body logging off, or trace export on

79 * Fixed agent-team teammates in tmux/iTerm2 panes sometimes staying open after acknowledging a shutdown request

80 * Fixed the keyless Console sign-in ("Sign in with your Console account") not applying your organization's server-managed settings, and `/status` not showing the Organization for that sign-in

81 * Improved rendering performance: less re-render work per turn in long conversations, streaming no longer slows down as the reply grows, and background-agent updates no longer re-render the whole screen

82 * Improved prompt input responsiveness by reducing per-keystroke rendering work

83 * Improved policy helper diagnostics — refresh failures now show in `/status`, declining the managed-settings dialog prints why Claude Code exited, and helper timeouts are reported as timeouts

84 * Improved `/code-review --comment` to post findings on GitLab merge requests via `glab mr note` instead of reporting the target as unsupported

85 * Improved notifications: an MCP elicitation or permission ask queued under another dialog now sends its idle desktop notification at the same delay as a visible ask

86 * Improved verbose/transcript output: async hook completion notices that arrive together now appear on one line instead of one line per hook

87 * Improved `claude self-hosted-runner --configure-git` to also enable git push negotiation, so the first push of a new branch from a stale clone uploads only the new commits instead of the whole tree

88 * Improved liveness reporting to SDK hosts while a response is held open by gateway keep-alives, so long waits under a raised `CLAUDE_STREAM_IDLE_TIMEOUT_MS` are not mistaken for a hung session

89 * Improved MCP connection and OAuth debug/error logs so credentials carried in a server's URL or request headers are redacted

90 * Improved `/fork` to keep the original conversation's prompt cache in the new background session: its worktree briefing now arrives as a message instead of a system-prompt change

91 * Improved emoji autocomplete to accept the remaining GitHub/Slack shortcode aliases (`:satisfied:`, `:telephone:`, `:collision:`, …)

92 * Changed `--effort` to lift a new model's default-effort hold for that session only rather than permanently; an effort picked on claude.ai for a Remote Control session now applies during the hold

93 * Changed a `policyHelper` in MDM or `managed-settings.json` shadowed at launch by cached server-managed settings to run (or exit) as soon as the fetch reports them removed, not at the next launch

94 * Changed `managedSourcesBehavior: "merge"` to take `sandbox.credentials.awsPairs` and `sandbox.ripgrep` whole from the highest managed source that sets them instead of combining the sources' values

95 * Changed gateway model discovery (`CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1`) to run even when `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` is set, since it only queries your gateway

96 * Changed `claude --resume <session-id> --bg` to continue that session under its own ID when nothing is running it, instead of silently starting a copy; a copy is now announced

97 * Changed `/btw` history browsing from `←`/`→` to `Shift+←`/`Shift+→` (or `[`/`]`), stepping through your recent side questions and back to the live answer

98 * Changed `defaultMode: "bypassPermissions"` in `.claude/settings.json` or `.claude/settings.local.json` to be ignored, like `"auto"`; set it in user or managed settings, or pass `--permission-mode`

99 * Changed `fable` and `best` in Claude apps gateway sessions to keep resolving to Fable 5 for now, since gateways not yet configured for Fable 5.1 reject it; pick Fable 5.1 in `/model` to use it

100 * Changed `--add-dir`, `/add-dir`, and `additionalDirectories` to refuse network paths (UNC shares, `/net/<host>` automounts) with a message before touching them; on Windows use a mapped drive letter

101 * Changed Claude apps gateway sign-in and token refresh requests to verify the gateway's pinned TLS certificate, as the managed settings fetch already does

102 * Changed Cowork and claude.ai cloud sessions: reading an artifact that isn't yours now always asks you first, even in auto mode

103 * Removed the Ctrl+E command explanation on Bash and PowerShell permission prompts

104 * \[VSCode] Added collapsible ACCOUNT & USAGE and SESSION MANAGER section headers to the session list panel, with the account email, the usage meter, and a View details link opening the usage dialog

105 * \[VSCode] Added a model pill to the input footer that shows the current model and opens the model picker, with an Effort row and a "More models" page

106 * \[VSCode] Added a collapse toggle to the Ungrouped section of the session list

107 * \[VSCode] Added output style selection to the command menu, including custom styles

108 * \[VSCode] Fixed third-party provider deployments (Bedrock, Vertex, and others) still showing claude.ai-only features (remote sessions, dictation, usage) and calling claude.ai with a leftover login

109 * \[VSCode] Fixed the session list panel's usage meter staying blank after the panel loads; it now shows the last known usage immediately

110 * \[VSCode] Fixed the "Enable Remote Control for all sessions" toggle so turning it on or off applies to sessions that are already open, not only to new ones

111 * \[VSCode] Fixed screen reader announcements: a control character before a fence or heading no longer drops visible lines from speech, and bold markers spanning a heading are no longer mis-paired

112 * \[VSCode] Changed the action menu to list slash commands in a filterable "Slash commands" dialog instead of inline; picking one runs it; the MCP servers dialog gained the same filter box

113 * \[VSCode] Changed "Delete session" to "Archive session": archived sessions move to a collapsible "Archived sessions" group at the bottom of the list with an Unarchive action

114</Update>

115

9116<Update label="2.1.252" description="August 31, 2026">

10117 * Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs

11118 * Fixed "always allow" not saving in a project that has no .claude/settings.local.json yet

from line 2022

19152022 * Fixed `/autofix-pr` reporting "cannot run on the default branch" when the session is inside a git worktree or another repository

19162023 * Fixed `--resume` picker not showing sessions from the current directory when it isn't a git worktree (e.g., jj workspaces)

19172024 * Fixed Windows hooks that invoke bash explicitly (e.g., `/usr/bin/bash script.sh`) failing with "command not found" or "cannot execute binary file"

1918 * Fixed OpenTelemetry log events (`user_prompt`, `api_request`, `tool_result`, `tool_decision`) being silently dropped when emitted before telemetry initialization completed

1919 * Fixed `claude mcp` list/get/add printing secrets to the terminal: `${VAR}` references are no longer expanded, and credential headers and URL secrets are redacted

1920 * Fixed Workflow agents spawned with `isolation: "worktree"` in background sessions being blocked from editing files inside their own worktree

1921 * Fixed background sessions dispatched from `claude agents` booting on a stale model from the daemon's environment instead of the model in `settings.json`

1922 * Fixed a potential crash when rendering Write tool results after resuming a session

1923 * Fixed completed subagents getting stuck showing as running when an error occurs while finalizing their result

1924 * Fixed `EADDRINUSE` errors from tools that bind Unix sockets under `$TMPDIR` when `CLAUDE_CODE_TMPDIR` is set to a deep path

1925 * Improved terminal rendering performance by stabilizing the layout engine's JIT compilation profile

1926 * Improved rendering performance for large file writes

1927 * \[VSCode] Added a tip suggesting disabling terminal GPU acceleration (or running `/terminal-setup`) to fix garbled glyphs

1928</Update>

1929

1930<Update label="2.1.160" description="June 2, 2026">

1931 * Added a prompt before writing to shell startup files (`.zshenv`, `.zlogin`, `.bash_login`) and `~/.config/git/`, which could otherwise lead to unintended command execution

1932 * `acceptEdits` mode now prompts before writing build-tool config files that grant code execution (`.npmrc`, `.yarnrc*`, `bunfig.toml`, `.bazelrc`, `.pre-commit-config.yaml`, `.devcontainer/`, etc.)

1933 * Edit no longer requires a separate Read after viewing a file with `grep`: single-file `grep`/`egrep`/`fgrep` commands now satisfy the read-before-edit check

1934 * Fixed copy-on-select not writing to the Windows clipboard on WSL — now uses PowerShell interop instead of OSC 52, which terminals like MobaXterm don't support

1935 * Fixed restoring a completed session from `claude agents` dropping chat history and re-running the original prompt

1936 * Fixed background sessions re-attached after overnight retire losing their conversation and re-running the original prompt

1937 * Fixed `claude --bg` occasionally failing with "socket missing" when the background daemon was cold-starting on a loaded machine

1938 * Fixed an issue on Windows where the directory a background session was started in could not be deleted after `claude rm` until the background daemon exited

1939 * Fixed background agents that resumed work being shown under Completed in the agents list

1940 * Fixed `claude agents` freezing for several seconds when returning to the session list due to the auto-updater re-checking on every exit

1941 * Fixed Esc, arrow keys, and typing becoming unresponsive on Windows when attached to a background session or in the agent view while the host is under heavy CPU load

1942 * Fixed background agents emitting terminal sync-output markers to terminals that don't support them (Apple Terminal, tmux), causing render artifacts when entering a running agent

1943 * Fixed mouse wheel scrolling prompt history instead of the transcript right after opening a session from the agents list

1944 * Fixed CJK IME composition appearing at the bottom-left of the screen instead of at the input caret in the `claude agents` view

1945 * Fixed valid `file:///C:/...` links being rewritten to a broken path on Windows terminals with hyperlink support

1946 * Fixed voice mode failing to connect when the project directory or branch name contains non-ASCII or special characters

1947 * Fixed the auto mode unavailability message on third-party providers (Bedrock/Vertex/Foundry) to point to the `CLAUDE_CODE_ENABLE_AUTO_MODE` opt-in instead of incorrectly blaming the model

1948 * Fixed `/effort ultracode` incorrectly blaming the dynamic workflows setting when the model cannot run xhigh; ultracode is no longer offered on models that do not support it

1949 * Fixed model-not-found errors suggesting `--model` when running via the SDK or other hosts where the CLI flag doesn't apply

1950 * Fixed Claude's past replies disappearing from scrollback when resuming a brief mode session with brief mode turned off

1951 * Fixed vim mode `p` pasting on the line below instead of at the cursor when the register was yanked with `v$`

1952 * Improved performance of opening recently-inactive background agent sessions in `claude agents`

1953 * Improved auto mode classifier latency by reducing reasoning on routine actions, lowering the chance of "could not evaluate this action" blocks

1954 * Improved background-session teardown (`claude rm`/`stop`, idle reap) to send SIGTERM to running shell subprocesses before SIGKILL, so cleanup handlers run

1955 * Removed `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE`; the environment variable is now a no-op

1956 * Removed the JetBrains plugin install suggestion from startup

1957 * Renamed the dynamic-workflow trigger keyword from `workflow` to `ultracode`. The word "workflow" no longer triggers a run; asking for one in your own words still works. The trigger keyword is highlighted in violet in the prompt input

1958</Update>

1959

1960<Update label="2.1.159" description="May 31, 2026">

1961 * Internal infrastructure improvements (no user-facing changes)

1962</Update>

1963

1964<Update label="2.1.158" description="May 30, 2026">

1965 * Auto mode is now available on Bedrock, Vertex, and Foundry for Opus 4.7 and Opus 4.8. Opt in by setting `CLAUDE_CODE_ENABLE_AUTO_MODE=1`

1966</Update>

1967

1968<Update label="2.1.157" description="May 29, 2026">

1969 * Plugins in `.claude/skills` directories are now automatically loaded, no marketplace required

1970 * Added `claude plugin init <name>` to scaffold a new plugin in `.claude/skills`

1971 * Added autocomplete for `/plugin` arguments: subcommands, installed plugin names, and plugins from known marketplaces

1972 * `claude agents`: the `agent` field in `settings.json` is now honored for dispatched sessions, with `--agent <name>` to override it

1973 * `EnterWorktree` can now switch between Claude-managed worktrees mid-session

1974 * `tool_decision` telemetry events now include `tool_parameters` (bash commands, MCP/skill names) when `OTEL_LOG_TOOL_DETAILS=1`

1975 * Worktrees managed by Claude are now left unlocked when the agent finishes, so `git worktree remove`/`prune` can clean them up

1976 * Fixed unprocessable images (zero-byte, corrupt) attached via paste, MCP, or dialog crashing the request instead of becoming a text placeholder

1977 * Fixed sandbox network permission prompts appearing in auto and bypass-permissions mode when using the desktop app, IDE extensions, or SDK

1978 * Fixed `claude agents` completed sessions not retiring when an idle subagent was still parked or had leaked a backgrounded shell

1979 * Fixed `claude agents` pressing Esc not cancelling a slow "opening…", leaving the list unresponsive

1980 * Fixed background agent worktrees under `.claude/worktrees/` being orphaned after the 30-day job retention sweep

1981 * Fixed background sessions re-attached after a sleep/wake not telling the model the correct date

1982 * Fixed copy-on-select in `claude agents` not reaching the system clipboard inside tmux with `set-clipboard on` (regression in 2.1.153)

1983 * Fixed `--resume` not reporting background subagents that were running when the previous Claude Code process exited

1984 * Fixed the `--resume` session picker leaving its contents on the terminal after exiting in fullscreen mode

1985 * Fixed `--worktree` and `--worktree --tmux` returning to the canonical repo root instead of the current linked worktree

1986 * Fixed the `/model` picker showing an incorrect "Newer version available" hint when the selected model is already the newest in its family; the pinned-model row now shows the model's description instead of its raw ID

1987 * Fixed literal markdown markers (backticks, asterisks) appearing in the in-progress message text in fullscreen mode

1988 * Fixed the terminal freezing after approving the managed-settings security dialog at startup

1989 * Fixed a rare duplicate line appearing in scrollback after the terminal UI redraws

1990 * Fixed right-click paste duplicating the clipboard in the VS Code, Cursor, and Windsurf integrated terminals

1991 * WSL: fixed image paste (`alt+v` keybinding), screenshot paste on Windows 11, and added support for dragging images from Windows Explorer

1992 * Improved performance of long and resumed conversations by eliminating redundant message-rendering recomputations

1993 * `/terminal-setup` now disables GPU acceleration in VS Code/Cursor/Windsurf integrated terminals to prevent garbled-text rendering

1994 * The Feature of the Week credit-claim status now appears as a notification in the status area instead of a line above the prompt

1995 * `claude agents`: slash-command autocomplete in the dispatch input now matches substrings

1996 * Removed the "bash commands will be sandboxed" startup banner — sandbox status still shows in `/status` and when a command is blocked

1997 * Removed the "/ide for …" startup hint toast

1998 * \[IDE] Fixed clicking Stop while a background subagent is running not actually stopping it

1999 * \[VSCode] Fixed the fast mode indicator not appearing on Opus 4.8

2000 * Pressing backspace right after a workflow trigger keyword now dismisses the workflow request (same as alt+w) instead of deleting a character

2001 * Added a "Workflow keyword trigger" setting in /config to stop the word "workflow" in a prompt from triggering a dynamic workflow

2002</Update>

2003

2004<Update label="2.1.156" description="May 29, 2026">

2005 * Fixed an issue when using Opus 4.8 where thinking blocks were modified, leading to API errors.

2006</Update>

2007

2008<Update label="2.1.154" description="May 28, 2026">

2009 * Opus 4.8 is here! Now defaults to high effort · /effort xhigh for your hardest tasks

2010 * Introducing dynamic workflows: ask Claude to create a workflow and it orchestrates work across tens to hundreds of agents in the background, so you can take on larger, more complex tasks. Run `/workflows` to view your runs

2011 * Fast mode on Opus 4.8 is now available at a fraction of its previous cost: 2x the standard rate for 2.5x the speed

2012 * The lean system prompt is now the default for all models except Haiku, Sonnet, and Opus 4.7 and earlier

2013 * Claude now reserves the multiple-choice question prompt for decisions it genuinely cannot make itself, instead of asking when it already has enough context to proceed

2014 * `/simplify` now runs a cleanup-only review (reuse, simplification, efficiency, altitude) and applies the fixes, instead of running the full `/code-review --fix` bug-hunting review

2015 * Renamed the `/effort` slider labels from "Speed"/"Intelligence" to "Faster"/"Smarter" for clarity

2016 * `claude agents`: type `! <command>` to run a shell command as a background session you can attach to and detach from. Also available as `claude --bg --exec '<command>'`

2017 * `claude agents`: `/logout` now signs you out instead of being sent to a background session

2018 * `←←` to open the agents view now works on Bedrock, Vertex, Foundry, and with telemetry disabled

2019 * Claude in Chrome: pick which connected browser to use via `/chrome` → "Select browser…", or in-chat when a browser action runs with multiple connected

2020 * Plugins can now declare `defaultEnabled: false` in `plugin.json` or a marketplace entry; enable them with `/plugin` or `claude plugin enable`. Dependencies of enabled plugins are still enabled automatically

2021 * The `/plugin` Discover tab now pins plugins whose relevance signals match the current directory with a "suggested for this directory" annotation

2022 * Streaming tool execution is now always enabled, including when telemetry is disabled or on Bedrock/Vertex/Foundry (previously behind a feature flag)

2023 * Stdio MCP server subprocesses now receive `CLAUDE_CODE_SESSION_ID` and `CLAUDECODE=1` in their environment

2024 * `claude mcp list`/`get` now show unapproved `.mcp.json` servers as `⏸ Pending approval` instead of auto-approving and connecting when output is piped

2025 * `/remote-control` autocomplete now shows "Disconnect Remote Control" when Remote Control is already active

2026 * Added Claude Opus 4.8 support and 4.7 → 4.8 migration guidance to the `/claude-api` skill

2027 * Deprecated `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` (will be removed on 06/01). To use fast mode on Opus 4.6, switch with `/model claude-opus-4-6[1m]` and then `/fast on`

2028 * Improved the auto-mode classifier's detection of data exfiltration, particularly bulk transfers of repository contents

2029 * Fixed `rm -rf $HOME` not being blocked as a dangerous path when `HOME` has a trailing slash

2030 * Fixed `$TMPDIR` resolving to different directories in sandboxed vs unsandboxed Bash commands within the same session

2031 * Fixed unreadable highlighted-row text in `claude agents` when the Claude Code theme doesn't match the terminal background

2032 * Fixed background-agent completion notifications triggering premature "out of context" behavior on some 1M-context models

2033 * Fixed background-session classifier losing the user's goal when a scheduled `/command` fires

2034 * Fixed pinned background sessions respawning every minute after a Claude Code update, causing repeated agent-start notifications and process churn at idle

2035 * Fixed background sessions stuck at "blocked", "running", or "working" not retiring after the idle grace period

2036 * Fixed subagents in background sessions bypassing the worktree-isolation guard and writing to the shared checkout

2037 * Fixed orphaned `claude --bg-pty-host` processes spinning at 100% CPU after the daemon exits on macOS

2038 * Fixed number key shortcuts not working for options shown below the divider in option dialogs

2039 * Fixed `worktree.baseRef: "head"` resolving to the main checkout's HEAD instead of the current worktree's HEAD when spawning subagents or calling `EnterWorktree` from inside a linked worktree

2040 * Fixed a stray leading space on wrapped lines when the previous line ended exactly at the terminal width

2041 * Fixed intermittent terminal rendering corruption in VS Code by capping the number of distinct colors the thinking spinner produces

2042 * Fixed plan file names including `[Image #N]` / `[Pasted text #N]` placeholders when a plan-mode prompt starts with pasted images or text

2043 * Fixed a phantom expand/click affordance on colored tool output: short ANSI-colored lines that fit on screen no longer show a "ctrl+o to expand" hint

2044 * Fixed a single invalid `allowedMcpServers`/`deniedMcpServers` entry in managed settings discarding all managed-settings policy; the bad entry is now dropped with a `claude doctor` warning

2045 * Fixed API 400 errors on models that don't support the effort parameter when `CLAUDE_CODE_ALWAYS_ENABLE_EFFORT` is set

2046 * Windows: Fixed update failures caused by `claude.exe` being in use showing a generic error instead of telling you to close other sessions and retry

2047 * Removed the stale "& for background" hint from the shortcuts help panel

2048 * \[VSCode] Auto mode no longer requires the bypass-permissions setting to appear in the mode picker, and a dismissable notice on the new-session screen explains auto mode the first time it's active

2049 * Fixed the task panel below the prompt showing a stray unselectable "main" row when only a workflow is running

2050 * Fixed /mcp tools list and tool detail rendering when MCP servers have long or multi-line tool names or long descriptions

2051 * Fixed the /model picker not showing fast mode pricing on the Default option for API (pay-as-you-go) users when fast mode is on

2052 * Fixed auto mode incorrectly blocking actions with "could not evaluate this action" when the safety classifier ran out of output tokens while reasoning

2053</Update>

2054

2055<Update label="2.1.153" description="May 28, 2026">

2056 * Added `skipLfs` option to `github`/`git` plugin marketplace sources to skip Git LFS downloads during clone and update

2057 * Claude Code now shows a one-time notice when your npm global install can't auto-update; `/doctor` lists the fixes

2058 * Status line commands now receive `COLUMNS` and `LINES` environment variables so scripts can size output to the terminal width

2059 * `claude agents`: autocomplete in the dispatch input now suggests native slash commands and bundled skills, not just project skills

2060 * `claude agents`: PR column now shows `PR #N` for a single PR or `N PRs` for multiple

2061 * `claude doctor` now shows the result of your last update attempt

2062 * Combined the separate "needs authentication" startup notifications for MCP servers and connectors into a single message

2063 * macOS: background agents now appear as "Claude Code" in Privacy & Security and keep their permission grants across upgrades

2064 * Fixed stateful MCP servers without the optional GET SSE stream rec

2025 * Fixed OpenTelemetry log events (`user_prompt`, `api_request`, `tool_result`, `tool_decision`) being silently dropped when emitted before telemetry initializat

communications-kit Changed · +7 / -7 lines

from line 207

207207mid-session. *Sonnet* is the workhorse default for everyday feature work,

208208bugs, tests, and reviews. Reach for *Opus* on large refactors, gnarly

209209debugging, or anything high-stakes. Drop to *Haiku* for quick questions,

210formatting, and mechanical edits where speed wins. *Fable 5* is the most

210formatting, and mechanical edits where speed wins. *Fable* is the most

211211capable model for your hardest, longest-running tasks; it is not the

212212default, so select it with `/model fable`, and note that cybersecurity and

213213biology content falls back to Opus automatically. Opus 5 runs its own

from line 220

220220📖 Model configuration → https://code.claude.com/docs/en/model-config

221221```

222222

223| Model | Best for |

224| ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

225| Fable 5 | The hardest, longest-running tasks. Opt-in only: select it with `/model fable`. Cybersecurity or biology content [falls back to Opus](/docs/en/model-config#automatic-model-fallback) |

226| Opus | Large-scale refactors, complex debugging, architecture decisions, high-stakes changes. On Opus 5, cybersecurity or biology content triggers [automatic model fallback or a refusal](/docs/en/model-config#automatic-model-fallback) |

227| Sonnet | Everyday feature work, bug fixes, tests, documentation, code review. Recommended default. |

228| Haiku | Quick questions, formatting, mechanical edits, rapid iteration |

223| Model | Best for |

224| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

225| Fable | The hardest, longest-running tasks. Opt-in only: select it with `/model fable`. Cybersecurity or biology content [falls back to Opus](/docs/en/model-config#automatic-model-fallback) |

227| Sonnet | Everyday feature work, bug fixes, tests, documentation, code review. Recommended default. |

228| Haiku | Quick questions, formatting, mechanical edits, rapid iteration |

229229

230230**Quick wins to try first**

231231

desktop Changed · +4 / -4 lines

from line 84

8484

8585

8686

87Auto mode is available to all users on the Anthropic API and requires Claude Opus 4.6 or later, Sonnet 4.6 or later, or Fable 5. Organization administrators can turn auto mode off with the `disableAutoMode` key in [managed settings](#managed-settings).

87Auto mode is available to all users on the Anthropic API and requires Claude Opus 4.6 or later, Sonnet 4.6 or later, or a Fable model. Organization administrators can turn auto mode off with the `disableAutoMode` key in [managed settings](#managed-settings).

8888

8989In Enterprise deployments that route Desktop to Google Cloud's Agent Platform, auto mode is also available by default; see [Auto mode on Bedrock, Agent Platform, or Foundry](/docs/en/permission-modes#enable-auto-mode-on-bedrock-agent-platform-or-foundry) for the supported models.

9090

from line 633

633633

634634To set environment variables for local sessions and dev servers on any platform, open the environment dropdown in the prompt box, hover over **Local**, and click the gear icon to open the local environment editor. Variables you save here are stored encrypted on your machine and apply to every local session and preview server you start. You can also add variables to the `env` key in your `~/.claude/settings.json` file, though these reach Claude sessions only and not dev servers. See [environment variables](/docs/en/env-vars) for the full list of supported variables.

635635

636[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthropic API, set `MAX_THINKING_TOKENS` to `0` in the local environment editor to turn thinking off; this has no effect on Fable 5, which always uses extended thinking. With thinking turned off on the Anthropic API, Claude Code sends effort `high` instead of a higher level to models it knows [don't accept that combination](/docs/en/errors#effort-isnt-available-with-thinking-turned-off), such as Opus 5.

636[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthropic API, set `MAX_THINKING_TOKENS` to `0` in the local environment editor to turn thinking off; this has no effect on Fable models, which always use extended thinking. With thinking turned off on the Anthropic API, Claude Code sends effort `high` instead of a higher level to models it knows [don't accept that combination](/docs/en/errors#effort-isnt-available-with-thinking-turned-off), such as Opus 5.

637637

638On models with [adaptive reasoning](/docs/en/model-config#adjust-effort-level), `MAX_THINKING_TOKENS` values other than `0` are ignored because adaptive reasoning controls thinking depth instead. On Opus 4.6 and Sonnet 4.6, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` to `1` to use a fixed thinking budget; Fable 5, Sonnet 5, and Opus 4.7 and later always use adaptive reasoning and have no fixed-budget mode.

638On models with [adaptive reasoning](/docs/en/model-config#adjust-effort-level), `MAX_THINKING_TOKENS` values other than `0` are ignored because adaptive reasoning controls thinking depth instead. On Opus 4.6 and Sonnet 4.6, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` to `1` to use a fixed thinking budget; Fable models, Sonnet 5, and Opus 4.7 and later always use adaptive reasoning and have no fixed-budget mode.

639639

640640#### Local sessions on managed devices

641641

env-vars Changed · +8 / -7 lines

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

from line 145

145145| `ANTHROPIC_CUSTOM_MODEL_OPTION_DESCRIPTION` | Display description for the custom model entry in the `/model` picker. Defaults to `Custom model (<model-id>)` when not set |

146146| `ANTHROPIC_CUSTOM_MODEL_OPTION_NAME` | Display name for the custom model entry in the `/model` picker. Defaults to the model ID when not set |

147147| `ANTHROPIC_CUSTOM_MODEL_OPTION_SUPPORTED_CAPABILITIES` | Comma-separated list of [capabilities](/docs/en/model-config#customize-pinned-model-display-and-capabilities) the custom model supports, for example `effort,thinking`. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |

148| `ANTHROPIC_DEFAULT_FABLE_MODEL` | Model ID that the `fable` alias resolves to, and the ID Claude Code recognizes as Fable 5 for [automatic model fallback](/docs/en/model-config#automatic-model-fallback) on third-party providers. See [Model configuration](/docs/en/model-config#environment-variables) |

148| `ANTHROPIC_DEFAULT_FABLE_MODEL` | Model ID that the `fable` alias resolves to, and the ID Claude Code recognizes as a Fable model for [automatic model fallback](/docs/en/model-config#automatic-model-fallback) on third-party providers. See [Model configuration](/docs/en/model-config#environment-variables) |

149149| `ANTHROPIC_DEFAULT_FABLE_MODEL_DESCRIPTION` | Display description for the pinned Fable model in the `/model` picker. Defaults to `Custom Fable model` when not set. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |

150150| `ANTHROPIC_DEFAULT_FABLE_MODEL_NAME` | Display name for the pinned Fable model in the `/model` picker. Defaults to the model ID when not set. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |

151151| `ANTHROPIC_DEFAULT_FABLE_MODEL_SUPPORTED_CAPABILITIES` | Comma-separated list of [capabilities](/docs/en/model-config#customize-pinned-model-display-and-capabilities) the pinned Fable model supports, for example `effort,thinking`. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |

from line 220

220220| `CLAUDE_CODE_CONNECT_TIMEOUT_MS` | Removed in v2.1.186 and now a no-op. Previously set a separate timeout for the connect, TLS, and response-header phase of a streaming API request. Use `API_TIMEOUT_MS` for the per-request timeout. For the response-header phase of a streaming request, see `CLAUDE_STREAM_FIRST_BYTE_TIMEOUT_MS` |

221221| `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`](/docs/en/cli-reference#cli-flags) flag does both at once. Defaults to `~/.claude/debug/<session-id>.txt` |

222222| `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 |

223| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Set to `1` to disable [1M context window](/docs/en/model-config#extended-context) support. When set, 1M model variants are unavailable in the model picker, and Claude Code holds sessions on models with a native 1M window, such as [Sonnet 5](/docs/en/model-config#sonnet-5-context-window) and Fable 5, to a 200K window; see [Extended context](/docs/en/model-config#extended-context) for how the hold is enforced. Useful for enterprise environments with compliance requirements. For its role in correcting the window for an unrecognized `[1m]` model ID, see [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id) |

224| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/docs/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`. Has no effect on Fable 5, Sonnet 5, or Opus 4.7 and later, which always use adaptive reasoning |

223| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Set to `1` to disable [1M context window](/docs/en/model-config#extended-context) support. When set, 1M model variants are unavailable in the model picker, and Claude Code holds sessions on models with a native 1M window, such as [Sonnet 5](/docs/en/model-config#sonnet-5-context-window) and the Fable models, to a 200K window; see [Extended context](/docs/en/model-config#extended-context) for how the hold is enforced. Useful for enterprise environments with compliance requirements. For its role in correcting the window for an unrecognized `[1m]` model ID, see [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id) |

224| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/docs/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`. Has no effect on [Fable models](/docs/en/model-config#extended-thinking), Sonnet 5, or Opus 4.7 and later, which always use adaptive reasoning |

225225| `CLAUDE_CODE_DISABLE_ADMIN_ENV_UNION` | Set to `1` to stop Claude Code from merging [managed settings](/docs/en/managed-settings#precedence-within-the-managed-tier) `env` blocks per key across admin sources, so only the highest-priority source's whole `env` block applies, as before v2.1.223. Set it in the environment that launches Claude Code, since Claude Code ignores a copy delivered through a settings `env` block. Requires Claude Code v2.1.223 or later |

226226| `CLAUDE_CODE_DISABLE_ADVISOR_TOOL` | Set to `1` to disable the [advisor tool](/docs/en/advisor). The `/advisor` command becomes unavailable, any configured `advisorModel` is ignored, and the `--advisor` flag is accepted but has no effect, so existing scripts that pass it continue to work without errors |

227227| `CLAUDE_CODE_DISABLE_AGENT_VIEW` | Set to `1` to turn off [background agents and agent view](/docs/en/agent-view): `claude agents`, `--bg`, `/background`, and the on-demand supervisor. Equivalent to the [`disableAgentView`](/docs/en/settings-reference#disableagentview) setting |

from line 254

254254| `CLAUDE_CODE_DISABLE_PERMISSION_PROMPT_NOTIFY_HOOKS` | Set to `1` to stop Claude Code from running your [`Notification` hooks for unanswered permission requests](/docs/en/hooks#notification) in sessions where Claude Code sends them to the Agent SDK's `canUseTool` callback, which is how Claude Desktop and the VS Code extension host Claude Code. Has no effect in terminal sessions. Requires Claude Code v2.1.233 or later |

255255| `CLAUDE_CODE_DISABLE_POLICY_SKILLS` | Set to `1` to skip loading skills from the system-wide managed skills directory. Useful for container or CI sessions that should not load operator-provisioned skills |

256256| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Set to `1` to disable automatic terminal title updates based on conversation context. In Agent SDK and `claude -p` sessions, this also skips the background small/fast-model request that generates the session title |

257| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to omit the `thinking` parameter from API requests entirely. This is a compatibility option for proxies and gateways that reject the parameter. The variable's behavior is unchanged from earlier versions; on models that think by default, omitting the parameter means the model may still think. To explicitly disable [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) on the Anthropic API, use `MAX_THINKING_TOKENS=0` instead, which is also ineffective on Fable 5 since it cannot have thinking turned off. On [third-party providers](/docs/en/third-party-integrations), `0` likewise omits the parameter, so the two variables behave the same there |

257| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to omit the `thinking` parameter from API requests entirely. This is a compatibility option for proxies and gateways that reject the parameter. The variable's behavior is unchanged from earlier versions; on models that think by default, omitting the parameter means the model may still think. To explicitly disable [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) on the Anthropic API, use `MAX_THINKING_TOKENS=0` instead, which is also ineffective on [Fable models](/docs/en/model-config#extended-thinking) since they can't have thinking turned off. On [third-party providers](/docs/en/third-party-integrations), `0` likewise omits the parameter, so the two variables behave the same there |

258258| `CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT` | Set to `1` to skip proactive [auto-compaction](/docs/en/costs#reduce-token-usage) when Claude Code doesn't recognize the model ID, such as an [LLM gateway](/docs/en/llm-gateway) alias. Without this variable, Claude Code compacts at the context window it assumes for the ID. `CLAUDE_CODE_MAX_CONTEXT_TOKENS` can correct the assumed window instead; see [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id) for when each variable applies. Requires Claude Code v2.1.223 or later |

259259| `CLAUDE_CODE_DISABLE_VIRTUAL_SCROLL` | Set to `1` to disable virtual scrolling in [fullscreen rendering](/docs/en/fullscreen) and render every message in the transcript. Use this if scrolling in fullscreen mode shows blank regions where messages should appear |

260260| `CLAUDE_CODE_DISABLE_WORKFLOWS` | Set to `1` to disable [workflows](/docs/en/workflows#turn-workflows-off). Equivalent to the [`disableWorkflows`](/docs/en/settings-reference#disableworkflows) setting |

from line 319

319319| `CLAUDE_CODE_PERFORCE_MODE` | Set to `1` to enable Perforce-aware write protection. When set, Edit, Write, and NotebookEdit fail with a `p4 edit <file>` hint if the target file lacks the owner-write bit, which Perforce clears on synced files until `p4 edit` opens them. This prevents Claude Code from bypassing Perforce change tracking |

320320| `CLAUDE_CODE_PLUGIN_CACHE_DIR` | Override the plugins root directory. Despite the name, this sets the parent directory, not the cache itself: marketplaces and the plugin cache live in subdirectories under this path. Defaults to `~/.claude/plugins` |

321321| `CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS` | Timeout in milliseconds for git operations when installing or updating plugins (default: 120000). Increase this value for large repositories or slow network connections. See [Git operations time out](/docs/en/plugin-marketplaces#git-operations-time-out) |

322| `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE` | Set to `1` to skip the re-clone attempt and keep using the existing marketplace cache when a `git pull` fails. Useful in o

322| `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE` | Set to `1` to skip the re-clone attempt and keep using the existing marketplace cache when a `git pull` fails. U

errors Changed · +24 / -8 lines

### Claude Code does not support this model

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

from line 113

113113| `There's an issue with the selected model` | [Request errors](#theres-an-issue-with-the-selected-model) |

114114| `Model ... is not a recognized model id` | [Request errors](#model-is-not-a-recognized-model-id) |

115115| `Claude Opus is not available with the Claude Pro plan` | [Request errors](#claude-opus-is-not-available-with-the-claude-pro-plan) |

116| `Claude Code ... does not support this model; version ... or newer is required` | [Request errors](#claude-code-does-not-support-this-model) |

116117| `Model ... is restricted by your organization's settings` | [Request errors](#model-is-restricted-by-your-organizations-settings) |

117118| `thinking.type.enabled is not supported for this model` | [Request errors](#thinking-type-enabled-is-not-supported-for-this-model) |

118119| `Effort '<level>' isn't available with thinking turned off on this model` | [Request errors](#effort-isnt-available-with-thinking-turned-off) |

from line 535

534535

535536### The prompt to confirm went unanswered

536537

537On plans where Fable 5 usage [bills to usage credits](/docs/en/model-config#fable-5-and-usage-credits), Claude Code asks you to confirm before a request bills them. When nobody answers that consent prompt in a session that may have no one at its terminal, Claude Code closes the prompt and ends the turn with one of these messages:

538If your account requires the [Fable usage-credits consent](/docs/en/model-config#fable-and-usage-credits), Claude Code asks you to confirm before a Fable request bills usage credits. When nobody answers that consent prompt in a session that may have no one at its terminal, Claude Code closes the prompt and ends the turn with one of these messages:

538539

539540```text theme={null}

540Fable 5 limit reached · continuing on Fable 5 uses usage credits, and the prompt to confirm went unanswered — nothing was sent · answer it where this session is running, or /model to change

541Fable 5 now uses usage credits · the prompt to confirm went unanswered — nothing was sent · answer it where this session is running, or /model to change

541Fable limit reached · continuing on Fable 5.1 uses usage credits, and the prompt to confirm went unanswered — nothing was sent · answer it where this session is running, or /model to change

542Fable 5.1 now uses usage credits · the prompt to confirm went unanswered — nothing was sent · answer it where this session is running, or /model to change

542543```

543544

545The messages name the session's Fable model, so on Fable 5 they read `continuing on Fable 5` and `Fable 5 now uses usage credits`. Before v2.1.255, the first message began `Fable 5 limit reached`.

546

544547This happens in [Remote Control](/docs/en/remote-control) sessions, [background sessions](/docs/en/agent-view), and [agent team](/docs/en/agent-teams) teammate sessions. Claude Code shows the consent prompt only in the session's own interactive view: the terminal where it runs, or, for a background session, the [agents view](/docs/en/agent-view) once you attach. A Remote Control client can't display it. Claude Code closes the prompt at the [`dialogExpiry`](/docs/en/settings-reference#dialogexpiry) deadline, five minutes by default, or as soon as a new prompt arrives while nobody has typed at that terminal, such as a prompt sent from a Remote Control client. Typing at the terminal where the session runs cancels the deadline, and Claude Code waits for your answer. In a background session's attached view, typing doesn't cancel the deadline, and a new prompt still closes the consent prompt, so answer before either happens. Claude Code sends nothing and keeps your model, so when you send your next prompt, Claude Code shows the consent prompt again.

545548

546549**What to do:**

from line 1649

16461649**What to do:**

16471650

16481651* Run `/model` with no argument to open the picker and choose from the models available to your account, then pass the alias or ID shown there

1649* If you used an alias that a newer Claude Code version supports, run `claude update`. A full ID that starts with `claude-` passes this check even when the model is newer than your Claude Code version, so upgrading isn't needed for those.

1652* If you used an alias that a newer Claude Code version supports, run `claude update`. A full ID that starts with `claude-` passes this local check even when the model is newer than your Claude Code version. The server can still require a minimum version for that model; see [Claude Code does not support this model](#claude-code-does-not-support-this-model).

16501653* A model saved before v2.1.200 isn't repaired by this check. If a stale value keeps coming back, remove it from the locations listed under [Setting your model](/docs/en/model-config#setting-your-model).

16511654* The check runs only on the Anthropic API. On any other provider or gateway, including a custom `ANTHROPIC_BASE_URL`, the provider defines the model names, so Claude Code accepts any string and passes it through. Claude Code can still write the [unrecognized-model diagnostic line](#unrecognized-model-id-on-a-request) at request time, on every provider.

16521655

from line 1667

16641667* If you upgraded your plan recently and still see this, run `/logout` then `/login`. The stored token reflects your plan at the time you signed in, so upgrading on the web does not take effect in an existing session until you re-authenticate.

16651668* See [claude.com/pricing](https://claude.com/pricing) for which models each plan includes

16661669

1670### Claude Code does not support this model

1671

1672The model you selected requires a newer Claude Code version than the one making the request. The server checks this per model.

1673

1674```text theme={null}

1675API Error: 400 Claude Code 2.1.219 does not support this model; version 2.1.255 or newer is required. Run 'claude update', or update the Claude desktop app, then try again.

1676```

1677

1678**What to do:**

1679

1680* Run `claude update`, or update the Claude desktop app, then start a new session on the model

1681* To keep working in the current session, switch to another model with `/model`

1682

16671683<h3 id="model-is-restricted-by-your-organizations-settings">

16681684 Model is restricted by your organization's settings

16691685</h3>

from line 2378

23622378

23632379## Plugin errors

23642380

2365These errors come from [plugin](/docs/en/plugins) and [marketplace](/docs/en/plugin-marketplaces) configuration. For plugin problems that don't produce one of the messages on this page, such as a marketplace URL that doesn't load or a plugin that installs but doesn't appear, see [Plugin troubleshooting](/docs/en/discover-plugins#troubleshooting).

2366

2367### Marketplace is registered from an untrusted source

2368

2369The marketplace is registered under a name that is [reserved for official Anthropic marketplaces](/docs/en/plugin-marketplaces#marketplace-schema), but its registered source isn't an `anthropics` GitHub repository. Claude Code re-checks reserved names every time it loads or refreshes a marketplace, so the marketplace and the plugins installed from it stop loading. Before v2.1.205, the name was checked only when the marketplace was added, so an entry registered before its name became reserved kept loading.

2370

2371```text theme={null}

2372Marketplace "claude-community" is registered from an untrusted source: The name 'claude-community' is reserved for official Anthropic marketplaces. Only repositories from 'github.com/anthropics/' can use this name. To fix it, remove the marketplace and re-add it from the official source.

2373```

2374

2375**What to do:**

2376

2377* Run `claude plugin marketplace remove <name>`, then add the marketplace again from the official `github.com/anthropics` repository

2378* If you publish a third-party marketplace that use

2381These errors come from [plugin](/docs/en/plugins) and [marketplace](/docs/en/plugin-marketplaces) configuration. For plugin problems that don't produce one of the messages on this page, such as a mark

feature-availability Changed · +4 / -4 lines

from line 205

205205</table>

206206

2072071 On Google Cloud's Agent Platform, web search is available for Claude 4 models and later.

2082 On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and Fable 5. See [Auto mode configuration](/docs/en/auto-mode-config). The built-in starting permission mode on these providers is Manual. See [which mode a session starts in](/docs/en/permission-modes#which-mode-a-session-starts-in). In v2.1.158 through v2.1.206, auto mode on these providers also required setting `CLAUDE_CODE_ENABLE_AUTO_MODE=1`; v2.1.207 removed the requirement.

2082 On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and the Fable models. See [Auto mode configuration](/docs/en/auto-mode-config). The built-in starting permission mode on these providers is Manual. See [which mode a session starts in](/docs/en/permission-modes#which-mode-a-session-starts-in). In v2.1.158 through v2.1.206, auto mode on these providers also required setting `CLAUDE_CODE_ENABLE_AUTO_MODE=1`; v2.1.207 removed the requirement.

2092093 Subject to your agreement with the cloud provider.

2102104 Dashboard and API only. [Contribution metrics](/docs/en/analytics#enable-contribution-metrics) requires a claude.ai Team or Enterprise organization.

2112115 Requires Claude Code v2.1.224 or later on macOS and Linux, including Linux inside WSL 2. On native Windows, requires Claude Code v2.1.234 or later. With API key authentication, messaging is same-machine only. On Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry, messaging is same-machine only and requires Claude Code v2.1.248 or later. Claude can find your [Claude Code on the web](/docs/en/claude-code-on-the-web) sessions and your sessions on other machines only from a session that is connected to [Remote Control](/docs/en/remote-control). To connect, you need a claude.ai sign-in and the other [Remote Control requirements](/docs/en/remote-control#requirements). See [Message sessions on other machines](/docs/en/cross-session-messaging#message-sessions-on-other-machines).

from line 225

225225 **Partial support:**

226226

227227 * [Desktop](/docs/en/desktop): only via [Claude Desktop on 3P](https://claude.com/docs/third-party/claude-desktop/overview)

228 * [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable 5 only

228 * [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable models only

229229 * [Cross-session messaging](/docs/en/cross-session-messaging): between your sessions on this machine only <a href="#fn5">5</a>

230230 * [Zero Data Retention](/docs/en/zero-data-retention): subject to your AWS agreement

231231

from line 251

251251

252252 * [Desktop](/docs/en/desktop): via [managed settings](https://claude.com/docs/third-party/claude-desktop/configuration) or [Claude Desktop on 3P](https://claude.com/docs/third-party/claude-desktop/overview)

253253 * [Web search](/docs/en/tools-reference#websearch-tool-behavior): Claude 4 models and later

254 * [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable 5 only

254 * [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable models only

255255 * [Cross-session messaging](/docs/en/cross-session-messaging): between your sessions on this machine only <a href="#fn5">5</a>

256256 * [Zero Data Retention](/docs/en/zero-data-retention): subject to your Google Cloud agreement

257257

from line 265

265265

266266 * [Desktop](/docs/en/desktop): only via [Claude Desktop on 3P](https://claude.com/docs/third-party/claude-desktop/overview)

267267 * [Web search](/docs/en/tools-reference#websearch-tool-behavior): [deployments hosted on Anthropic](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options) only

268 * [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable 5 only

268 * [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable models only

269269 * [Cross-session messaging](/docs/en/cross-session-messaging): between your sessions on this machine only <a href="#fn5">5</a>

270270 * [Zero Data Retention](/docs/en/zero-data-retention): subject to your Azure agreement

271271

model-config Changed · +60 / -51 lines

### Work with Fable #### Fable and usage credits ### Work with Fable 5 #### Fable 5 and usage credits

from line 26

2626| Model alias | Behavior |

2727| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

2828| **`default`** | Special value that clears any model override and reverts to the [runtime default for your account](#default-model-setting). Not itself a model alias |

29| **`best`** | Uses Fable 5 where your organization has access to it, otherwise the latest Opus model |

30| **`fable`** | Uses Claude Fable 5 for your hardest and longest-running tasks |

29| **`best`** | Uses the latest Fable model where it's available to you, otherwise the same model as `opus` |

30| **`fable`** | Uses the latest Fable model for your hardest and longest-running tasks |

3131| **`sonnet`** | Uses the latest Sonnet model for daily coding tasks |

3232| **`opus`** | Uses the latest Opus model for complex reasoning tasks |

3333| **`haiku`** | Uses the fast and efficient Haiku model for simple tasks |

from line 44

4444| Amazon Bedrock, Google Cloud's Agent Platform | Opus 5 | Sonnet 4.5 |

4545| Microsoft Foundry | Opus 4.6 | Sonnet 4.5 |

4646

47Unless you set `ANTHROPIC_DEFAULT_FABLE_MODEL`, the `fable` alias resolves to Fable 5.1. Before v2.1.255, it resolved to Fable 5.

4749Where an alias resolves to an older model, newer models are available by selecting the full model name explicitly or setting `ANTHROPIC_DEFAULT_OPUS_MODEL` or `ANTHROPIC_DEFAULT_SONNET_MODEL`.

4850

4951Before v2.1.219, `opus` resolved to Opus 4.8 on the Anthropic API from v2.1.154, and on Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform from v2.1.207. Before v2.1.207, `opus` resolved to Opus 4.7 on Claude Platform on AWS and to Opus 4.6 on Amazon Bedrock and Google Cloud's Agent Platform.

from line 56

5456 Opus 5 requires Claude Code v2.1.219 or later. Sonnet 5 requires v2.1.197 or later. Opus 4.8 requires v2.1.154 or later. Run `claude update` to upgrade.

5557</Note>

5658

57### Work with Fable 5

59### Work with Fable

5860

59[Claude Fable 5](https://platform.claude.com/docs/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5) is the most capable model in Claude Code, suited to tasks larger than a single sitting. It sustains long autonomous sessions, investigates before acting, and verifies its work more often than smaller models.

61[Claude Fable 5.1](https://platform.claude.com/docs/en/about-claude/models/overview) and Claude Fable 5 are the most capable models in Claude Code, suited to tasks larger than a single sitting. They sustain long autonomous sessions, investigate before acting, and verify their work more often than smaller models. Fable 5.1 is the newer release.

6062

61Fable 5 is not the default model. Select it with `/model fable`. Requests that its safety classifiers flag, most often in cybersecurity and biology domains, trigger [automatic model fallback](#automatic-model-fallback).

63Neither Fable model is the account-type default on any plan or provider. Select one explicitly:

6264

63To get the most from Fable 5:

65* **Fable 5.1**: run `/model fable`, or launch with `claude --model fable`.

66* **Fable 5**: select it by model ID. On the Anthropic API, run `/model claude-fable-5` or launch with `claude --model claude-fable-5`. On other providers, use your provider's Fable 5 model ID or [pin it](#pin-models-for-third-party-deployments) with `ANTHROPIC_DEFAULT_FABLE_MODEL`.

6467

68If your user settings hold `claude-fable-5` or `claude-fable-5[1m]` as the model, for example because you selected Fable in the `/model` picker before v2.1.255, and you connect to the Anthropic API directly, Claude Code changes that saved value to the `fable` or `fable[1m]` alias the first time you run v2.1.255 or later, and the startup model line shows `(auto-updated)` once. A `claude-fable-5` value in project, local, or managed settings is left as it is.

70Requests that a Fable model's safety classifiers flag, most often in cybersecurity and biology domains, trigger [automatic model fallback](#automatic-model-fallback).

72To get the most from Fable:

6574* **Describe the outcome, not the steps**: hand it the result you want and let it plan the path. To keep it working toward that outcome, [set a goal](/docs/en/goal).

6675* **Hand it ambiguous problems**: root-cause investigations, outage debugging, and architecture decisions are where the extra investigation and verification pay off.

6776* **Skip the verification reminders**: it verifies its own work with less prompting, so reminders to test or check are usually unnecessary.

from line 77

6877* **Size up larger tasks**: give it work you would normally break into pieces. It holds long sessions without losing the thread.

6978

7079<Note>

71 Fable 5 requires Claude Code v2.1.170 or later. Older versions do not show Fable 5 in the model picker and cannot select it. Run `claude update` to upgrade. Fable 5 is not available under [zero data retention](/docs/en/zero-data-retention), where the `/model` picker either omits it or shows it disabled.

80 Fable 5.1 requires Claude Code v2.1.255 or later. If a request for it from an older version fails, see [Claude Code does not support this model](/docs/en/errors#claude-code-does-not-support-this-model). Fable 5 requires v2.1.170 or later. Run `claude update` to upgrade. For availability under zero data retention, see [Model availability under ZDR](/docs/en/zero-data-retention#model-availability-under-zdr).

7281</Note>

7382

74On the Anthropic API, the `/model` picker lists Fable 5 only after the server reports it available for your organization. When you type `/model fable`, Claude Code checks availability with the server directly, so the selection can succeed before the picker lists the entry.

83On the Anthropic API, the `/model` picker lists a Fable model only after the server reports it available for your organization. When you type `/model fable` or a Fable model ID, Claude Code checks availability with the server directly, so the selection can succeed before the picker lists the entry.

7584

76#### Fable 5 and usage credits

85#### Fable and usage credits

7786

78Depending on your plan and seat tier, Fable 5 usage can bill to [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) instead of drawing on your plan's included limits. When it does, the `/model` picker shows "Requires usage credits" on the Fable 5 row. To manage usage credits, see [Add usage credits to your subscription](/docs/en/costs#add-usage-credits-to-your-subscription).

87Depending on your plan and seat tier, Fable usage can bill to [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) instead of drawing on your plan's included limits. When it does, the `/model` picker shows "Requires usage credits" on the Fable row. To manage usage credits, see [Add usage credits to your subscription](/docs/en/costs#add-usage-credits-to-your-subscription).

7988

80In interactive sessions, Claude Code shows a consent prompt before a Fable 5 request bills usage credits. Members of Enterprise plans with organization billing don't see the prompt. You can continue on Fable 5 using usage credits or switch to your default model. You can also dismiss the prompt:

89In interactive sessions, Claude Code shows a consent prompt before a Fable request bills usage credits. Members of Enterprise plans with organization billing don't see the prompt. You can continue on Fable using usage credits or switch to your default model. You can also dismiss the prompt:

8190

8291* In the `/model` picker, you keep your current model.

8392* Mid-session, Claude Code continues the turn on your default model.

8493

85After you choose to continue on Fable 5 using usage credits, Claude Code doesn't show the prompt again.

94After you choose to continue on Fable using usage credits, Claude Code doesn't show the prompt again.

8695

8796In a session with [Remote Control](/docs/en/remote-control) connected, a [background session](/docs/en/agent-view), or an [agent team](/docs/en/agent-teams) teammate's session, nobody may be at the terminal, so Claude Code holds the mid-session consent prompt for the [`dialogExpiry`](/docs/en/settings-reference#dialogexpiry) deadline, five minutes by default. If nobody has answered by the deadline, Claude Code ends the turn without sending the request and adds a notice to the transcript, which the Remote Control client also shows. Your model selection is unchanged, and Claude Code asks for consent again on your next message.

8897

from line 101

92101* In a background session, answer before the deadline.

93102* If you send a new message from the remote client before anyone has typed at the terminal, Claude Code ends the turn the same way, and your new message starts the next turn. After someone types at the terminal, Claude Code keeps waiting for the answer and queues your new message behind it.

94103

95In [non-interactive mode](/docs/en/headless) with the `-p` flag and through the Agent SDK, Claude Code never shows the consent prompt. When a Fable 5 request there would bill to usage credits, Claude Code bills it without asking.

104In [non-interactive mode](/docs/en/headless) with the `-p` flag and through the Agent SDK, Claude Code never shows the consent prompt. When a Fable request there would bill to usage credits, Claude Code bills it without asking.

96105

97106### Setting your model

98107

from line 194

185194

186195## Restrict model selection

187196

188Enterprise administrators can use `availableModels` in [managed or policy settings](/docs/en/managed-settings) to restrict which models users can select. Entries match a model family such as `sonnet`, a version prefix such as `claude-sonnet-4-5`, or a full model ID such as `claude-sonnet-4-5-20250929`.

197Enterprise administrators can use `availableModels` in [managed or policy settings](/docs/en/managed-settings) to restrict which models users can select. Entries match a model family such as `sonnet`, a version prefix such as `claude-sonnet-4-5`, or a full model ID such as `claude-sonnet-4-5-20250929`. A version prefix also matches later model IDs that extend it with another segment, so `claude-fable-5` permits both Fable 5 and Fable 5.1, while `claude-fable-5-1` permits Fable 5.1 only.

189198

190199On platforms that embed Claude Code and set [`CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST`](/docs/en/env-vars), the host's model configuration takes precedence over managed model settings, while a managed `availableModels` allowlist stays in force unless the host supplies its own; [Exceptions to managed settings precedence](/docs/en/settings#exceptions-to-managed-settings-precedence) says which keys and variables the host overrides.

191200

from line 208

199208* **Advisor model**: the configured [`advisorModel`](/docs/en/advisor) setting and the `--advisor` flag

200209* **Background agent model**: the model selected in the [dispatch picker](/docs/en/agent-view)

201210

202On the Anthropic API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws), a model family alias, `opus`, `sonnet`, `haiku`, or `fable`, resolves to the newest version of its family that the allowlist permits. When the allowlist pins specific versions, for example `["sonnet", "claude-opus-4-6"]`, both `/model opus` and `--model opus` select Claude Opus 4.6, the newest permitted Opus, and show a notice naming both the requested and substituted models. Before v2.1.205, an alias whose newest released version was outside the list was rejected or replaced like any other blocked selection, even when the list permitted an older version.

211On the Anthropic API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws), a model family alias, `opus`, `sonnet`, `haiku`, or `fable`, resolves to its usual model when the allowlist permits that model. When the allowlist blocks that model, Claude Code substitutes the newest version of the family that the allowlist permits and shows a notice naming both the requested and substituted models. With `["sonnet", "claude-opus-4-6"]`, for example, both `/model opus` and `--model opus` select Claude Opus 4.6, the newest permitted Opus. Before v2.1.205, an alias whose newest released version was outside the list was rejected or replaced like any other blocked selection, even when the list permitted an older version.

203212

204213The substitution needs a permitted version to land on: when the allowlist permits no version of the alias's family, the alias follows the rejection and replacement behavior below like any other blocked value.

205214

from line 233

224233* **[Fallback model chains](#fallback-model-chains)**: entries outside the allowlist are dropped

225234* **Plan-mode upgrades**: on the Anthropic API and Claude Platform on AWS, an upgrade such as [`opusplan`](#opusplan-model-setting) to an excluded model uses the newest permitted version of the upgrade family. On providers with provider-specific model IDs, and when no version is permitted, the upgrade is skipped and planning continues on the session's model

226235* **[Automatic model fallback](#automatic-model-fallback)**: a fallback whose target is excluded does not run, so the flagged request ends with a refusal instead

227* **[Auto mode classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)**: the classifier's Claude Sonnet 5 default applies only when the allowlist permits Sonnet 5. When it's excluded, the classifier runs on the session's model, which the allowlist already governs, or on an Opus model when the session runs on [Fable 5](#work-with-fable-5). On providers other than the Anthropic API, that Opus fallback runs on the provider's default Opus model without consulting the allowlist. Requires Claude Code v2.1.210 or later

236* **[Auto mode classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)**: the classifier's Claude Sonnet 5 default applies only when the allowlist permits Sonnet 5. When it's excluded, the classifier runs on the session's model, which the allowlist already governs, or on an Opus model when the session runs on a [Fable model](#work-with-fable). On providers other than the Anthropic API, that Opus fallback runs on the provider's default Opus model without consulting the allowlist. Requires Claude Code v2.1.210 or later

228237* **[Fast mode](/docs/en/fast-mode)**: enabling fast mode is refused when the model the session would run on afterward is outside the allowlist

229238

230239```json theme={null}

from line 327

318327

319328A restricted model is hidden from the `/model` picker. Selecting it by name with `--model`, the `ANTHROPIC_MODEL` environment variable, or the `model` setting shows the notice `Model "<name>" is restricted by your organization's settings. Using <model> instead.` and the session starts on an allowed model. Typing `/model <name>` for a restricted model is rejected with `Model '<name>' is restricted by your organization's settings. Run /model to choose a different model.` and the session keeps its current model.

320329

321A [model family alias](#restrict-model-selection) such as `opus` resolves to the newest version of its family that the organization permits, with the same substitution notice. `/model <alias>` is rejected only when every version of its family is restricted; an alias set with `--model`, `ANTHROPIC_MODEL`, or the `model` setting is still replaced at startup in that case. Before v2.1.205, a family alias was substituted or rejected based on its newest released version alone, even when an older version was allowed.

330A [model family alias](#restrict-model-selection) such as `opus` resolves to its usual model when the organization permits it. When the organization restricts that model, Claude Code substitutes the newest version of the family that the organization permits, with the same substitution notice. `/model <alias>` is rejected only when every version of its family is restricted; an alias set with `--model`, `ANTHROPIC_MODEL`, or the `model` setting is still replaced at startup in that case. Before v2.1.205, a family alias was substituted or rejected based on its newest released version alone, even when an older version was allowed.

322331

323332Restrictions apply org-wide or per role:

324333

from line 362

353362

354363* [`availableModels`](#restrict-model-selection) on its own doesn't apply to the organization default, so an organization default outside the allowlist still applies. When [`enforceAvailableModels`](#enforce-the-allowlist-for-the-default-model) is also set, an organization default outside the allowlist is remapped to the first allowlist entry, like any other Default

355364* an organization default that [organization model restrictions](#organization-model-restrictions) deny for your account is replaced by the newest allowed model in its family, or a lower-cost family when every version of it is restricted

356* an organization default that isn't available to your account at all, such as Fable 5 under [zero data retention](/docs/en/zero-data-retention), is skipped, and the Default option resolves as it would [without an organization default](#default-model-setting)

365* an organization default that isn't available to your account at all is skipped, and the Default option resolves as it would [without an organization default](#default-model-setting)

357366

358367As of v2.1.199, when the organization default is a different model family from your account type's usual default, the `/model` picker keeps a separate row for that usual family, so you can still switch to it for a session. In v2.1.196 through v2.1.198 that row is missing from the picker.

359368

from line 391

382391

383392When managed settings [enforce the allowlist for the Default model](#enforce-the-allowlist-for-the-default-model) and the account-type default is not in `availableModels`, `default` resolves to the enforced Default instead of the account-type default above. When both apply, the organization default replaces the account-type default first and enforcement then applies to it: an allowlisted organization default is kept, while one outside the list resolves to the enforced Default.

384393

385Fable 5 is not the default model on any account type. Sessions use Fable 5 only after you choose it, for example with `/model fable`, a `model` setting, or the `best` alias where Fable 5 is available. Choosing it with `/model` saves it as the selected model in your user settings, so later sessions start on Fable 5 until you change models.

394Fable models are not the account-type default on any plan or provider. Choosing one with `/model` saves it as the selected model in your user settings, so later sessions start on it. For the one-time change Claude Code makes to a saved Fable 5 selection in v2.1.255, see [Work with Fable](#work-with-fable).

386395

387396### `opusplan` model setting

388397

from line 443

434443

435444### Automatic model fallback

436445

437This section covers content-based fallback from Fable 5 and Opus 5. For availability-based fallback when a model is overloaded or unavailable, see [Fallback model chains](#fallback-model-chains).

446This section covers content-based fallback from Fable models and Opus 5. For availability-based fallback when a model is overloaded or unavailable, see [Fallback model chains](#fallback-model-chains).

438447

439Fable 5 and Opus 5 run with safety classifiers for cybersecurity and biology content. When a classifier flags a request and the flagged category has a fallback model, Claude Code re-runs the request on that model and shows a notice in the transcript. The fallback model depends on which model refused and which category was flagged:

448Fable models and Opus 5 run with safety classifiers, which most often flag cybersecurity and biology content. When a classifier flags a request and the flagged category has a fallback model, Claude Code re-runs the request on that model and shows a notice in the transcript. For those two categories, the fallback model depends on which model refused:

440449

441* **Fable 5**: biology-flagged requests re-run on Opus 5, and cybersecurity-flagged requests re-run on Opus 4.8.

450* **Fable 5.1 and Fable 5**: biology-flagged requests re-run on Opus 5, and cybersecurity-flagged requests re-run on Opus 4.8.

442451* **Opus 5**: cybersecurity-flagged requests re-run on Opus 4.8. Biology-flagged requests end with a refusal instead, because Opus 5 runs its own biology classifiers with no fallback model.

443452

444453On Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, Claude Code resolves these targets through your deployment instead, and if you set `ANTHROPIC_DEFAULT_OPUS_MODEL`, categories that have a fallback re-run on the pinned model; see [Enable fallback on Bedrock, Agent Platform, and Foundry](#enable-fallback-on-bedrock-agent-platform-and-foundry).

from line 480

471480

472481On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), and [Microsoft Foundry](/docs/en/microsoft-foundry), model IDs are provider-specific, so automatic fallback only operates when Claude Code can identify both models involved:

473482

474* Claude Code must recognize the current model as a fallback source. Fable 5 is recognized when the model ID contains `claude-fable-5`, matches the value of `ANTHROPIC_DEFAULT_FABLE_MODEL`, or is mapped with [`modelOverrides`](#override-model-ids-per-version). Opus 5 is recognized by its provider model ID or a [`modelOverrides`](#override-model-ids-per-version) mapping.

475* The fallback model must resolve in your deployment. If you set `ANTHROPIC_DEFAULT_OPUS_MODEL`, flagged requests re-run on that model for every category that has a fallback; a biology flag on Opus 5 still ends with a refusal. If you don't set it, cybersecurity-flagged requests re-run on an Opus 4.8 entry in the provider's model list, and biology-flagged requests from Fable 5 on an Opus 5 entry.

483* Claude Code must recognize the current model as a fallback source. Fable 5.1 and Fable 5 are recognized when the model ID contains `claude-fable-5`, matches the value of `ANTHROPIC_DEFAULT_FABLE_MODEL`, or is mapped with [`modelOverrides`](#override-model-ids-per-version). Opus 5 is recognized by its provider model ID or a [`modelOverrides`](#override-model-ids-per-version) mapping.

484* The fallback model must resolve in your deployment. If you set `ANTHROPIC_DEFAULT_OPUS_MODEL`, flagged requests re-run on that model for every category that has a fallback; a biology flag on Opus 5 still ends with a refusal. If you don't set it, cybersecurity-flagged requests re-run on an Opus 4.8 entry in the provider's model list, and biology-flagged requests from a Fable model on an Opus 5 entry.

476485

477If either model can't be identified, Claude Code does not switch automatically. The flagged request ends with a refusal message, and you can switch models with [`/model`](#setting-your-model) and retry. Setting `ANTHROPIC_DEFAULT_FABLE_MODEL` to your Fable 5 model ID enables Fable 5 recognition. Setting `ANTHROPIC_DEFAULT_OPUS_MODEL` to an Opus model ID gives the flagged categories a fallback target, unless the pin names a model outside the Opus family or the model that refused; then Claude Code doesn't switch and the refusal stands.

486If either model can't be identified, Claude Code does not switch automatically. The flagged request ends with a refusal message, and you can switch models with [`/model`](#setting-your-model) and retry. Setting `ANTHROPIC_DEFAULT_FABLE_MODEL` to your Fable model ID enables Fable recognition. Setting `ANTHROPIC_DEFAULT_OPUS_MODEL` to an Opus model ID gives the flagged categories a fallback target, unless the pin names a model outside the Opus family or the model that refused; then Claude Code doesn't switch and the refusal stands.

478487

479488#### Security research and biology workloads

480489

481Workloads in offensive security or biology, including penetration testing, Capture the Flag (CTF) exercises, and biology-adjacent codebases, trigger fallback frequently, often on the first request. For substantive biology work on Fable 5, Claude Code moves the session to Opus 5 at the first flagged request, and later biology-flagged requests end in refusals there, because Opus 5 has no biology fallback. On Opus 5, you get those refusals from the first flagged request.

490Workloads in offensive security or biology, including penetration testing, Capture the Flag (CTF) exercises, and biology-adjacent codebases, trigger fallback frequently, often on the first request. For substantive biology work on Fable 5.1 or Fable 5, Claude Code moves the session to Opus 5 at the first flagged request, and later biology-flagged requests end in refusals there, because Opus 5 has no biology fallback. On Opus 5, you get those refusals from the first flagged request.

482491

483492This is expected routing for these domains, not an account flag. If your organization needs Fable-class capability for this work, ask your Anthropic account team about trusted access programs.

484493

from line 499

490499

491500| Model | Levels |

492501| :--------------------------------------- | :-------------------------------------- |

493| Fable 5 | `low`, `medium`, `high`, `xhigh`, `max` |

502| Fable 5.1 and Fable 5 | `low`, `medium`, `high`, `xhigh`, `max` |

494503| Opus 5, Sonnet 5, Opus 4.8, and Opus 4.7 | `low`, `medium`, `high`, `xhigh`, `max` |

495504| Opus 4.6 and Sonnet 4.6 | `low`, `medium`, `high`, `max` |

496505

from line 508

499508With the [`ultracode`](/docs/en/settings-reference#ultracode) setting off, Claude Code resolves the session's effort level in this order, taking the first that applies:

500509

5015101. An explicit choice: the [`CLAUDE_CODE_EFFORT_LEVEL`](/docs/en/env-vars#variables) environment variable, launching with `--effort`, or `/effort` in the session ([a non-interactive `/effort` has narrower effect](#non-interactive-effort))

5022. The model's default effort, on Fable 5, Opus 4.8, or Opus 4.7: from the first time you run one of these models, Claude Code holds that model's default effort across sessions, even when your settings resolve a different level, until you change effort once, for example with an interactive `/effort`, the `/model` picker's effort slider, or `--effort` at launch. Opus 5 has no such hold

5112. The model's default effort, on Fable 5, Opus 4.8, or Opus 4.7: from the first time you run one of these models, Claude Code holds that model's default effort across sessions, even when your settings resolve a different level, until you change effort once, for example with an interactive `/effort`, the `/model` picker's effort slider, or `--effort` at launch. Opus 5 and Fable 5.1 have no such hold

5035123. Your settings: the level you saved for the model or an [`effortLevel`](/docs/en/settings-reference#effortlevel) key, with the precedence between them and across settings files stated at [`modelSettings`](/docs/en/settings-reference#modelsettings)

5045134. The model's default effort: `high` on every model that supports effort, except that Opus 4.7 defaults to `xhigh` and, when your organization sets a default effort level for its [organization default model](#organization-default-model), that level is the default when you run that model

505514

from line 580

571580

572581Adaptive reasoning makes thinking optional on each step, so Claude can respond faster to routine prompts and reserve deeper thinking for steps that benefit from it. If you want Claude to think more or less often than the current level produces, you can say so directly in your prompt or in `CLAUDE.md`; the model responds to that guidance within its effort setting.

573582

574Fable 5, Sonnet 5, and Opus 4.7 and later always use adaptive reasoning. The fixed thinking budget mode and `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` do not apply to them.

583Fable 5.1, Fable 5, Sonnet 5, and Opus 4.7 and later always use adaptive reasoning. The fixed thinking budget mode and `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` do not apply to them.

575584

576585On Opus 4.6 and Sonnet 4.6, you can set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1` to revert to the previous fixed thinking budget controlled by `MAX_THINKING_TOKENS`. See [environment variables](/docs/en/env-vars).

577586

from line 588

579588

580589Extended thinking is the reasoning Claude emits before responding. On models that support [adaptive reasoning](#adjust-effort-level), the effort level is the primary control for how much thinking happens; the settings below turn thinking on or off and control how it displays. With thinking turned off on the Anthropic API, Claude Code sends effort `high` instead of a higher level to models it knows [don't accept that combination](/docs/en/errors#effort-isnt-available-with-thinking-turned-off), such as Opus 5.

581590

582| Control | How to set it |

583| :-------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

584| Toggle for the current session | Press `Option+T` on macOS or `Alt+T` on Windows and Linux |

585| Set the global default | Run `/config` and toggle thinking mode. Saved as `alwaysThinkingEnabled` in `~/.claude/settings.json` |

586| Disable through an environment variable | Set [`MAX_THINKING_TOKENS=0`](/docs/en/env-vars), which turns thinking off on the Anthropic API except on Fable 5. On [third-party providers](/docs/en/third-party-integrations) this omits the `thinking` parameter instead, and adaptive-reasoning models may still think. Other values apply only with a [fixed thinking budget](#adaptive-reasoning-and-fixed-thinking-budgets) |

591| Control | How to set it |

592| :-------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

593| Toggle for the current session | Press `Option+T` on macOS or `Alt+T` on Windows and Linux |

594| Set the global default | Run `/config` and toggle thinking mode. Saved as `alwaysThinkingEnabled` in `~/.claude/settings.json` |

595| Disable through an environment variable | Set [`MAX_THINKING_TOKENS=0`](/docs/en/env-vars), which turns thinking off on the Anthropic API except on Fable 5.1 and Fable 5. On [third-party providers](/docs/en/third-party-integrations) this omits the `thinking` parameter instead, and adaptive-reasoning models may still think. Other values apply only with a [fixed thinking budget](#adaptive-reasoning-and-fixed-thinking-budgets) |

587596

588Thinking cannot be turned off on Fable 5. The session toggle, `alwaysThinkingEnabled`, and `MAX_THINKING_TOKENS=0` have no effect there, and Fable 5 decides per step how much to think based on the effort level.

597Thinking cannot be turned off on Fable 5.1 or Fable 5. The session toggle, `alwaysThinkingEnabled`, and `MAX_THINKING_TOKENS=0` have no effect there, and the model decides per step how much to think based on the effort level.

589598

590599Claude Code collapses thinking output by default. Press `Ctrl+O` to toggle verbose mode and see the reasoning as gray italic text. Interactive sessions on the Anthropic API receive redacted thinking blocks by default, so set `showThinkingSummaries: true` in [settings](/docs/en/settings) if you want the full summaries available when you expand. You are charged for all thinking tokens generated, even when collapsed or redacted.

591600

592601### Extended context

593602

594Fable 5, Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes-by-model) for long sessions with large codebases.

603Fable 5.1, Fable 5, Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes-by-model) for long sessions with large codebases.

595604

596Availability varies by model and plan. On the Anthropic API, Fable 5, Sonnet 5, and Opus 4.7 and later always run with the 1M window.

605Availability varies by model and plan. On the Anthropic API, Fable 5.1, Fable 5, Sonnet 5, and Opus 4.7 and later run with the 1M window by default.

597606

598607On Max, Team, and Enterprise plans, including both Team Standard and Team Premium seats, Opus is automatically upgraded to 1M context with no additional configuration. Sonnet 4.6 with 1M context is not part of the automatic upgrade and requires [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) on every subscription plan, including Max.

599608

from line 614

605614

606615Claude Code checks these plan requirements only when it connects to the Anthropic API directly. If you point `ANTHROPIC_BASE_URL` at an [LLM gateway](/docs/en/llm-gateway#subscriptions-and-gateways) and your saved claude.ai login stays the active credential, Claude Code doesn't check your plan's usage credits. The `[1m]` options stay available in `/model`, and the gateway decides whether the request succeeds. Before v2.1.229, Claude Code rejected `/model sonnet[1m]` in that configuration when it couldn't confirm usage credits on the account.

607616

608To turn off 1M context, set `CLAUDE_CODE_DISABLE_1M_CONTEXT=1`. Claude Code removes 1M model variants from the model picker. On models with a native 1M window, such as Sonnet 5 and Fable 5, it also treats the model as having a 200K context window:

617To turn off 1M context, set `CLAUDE_CODE_DISABLE_1M_CONTEXT=1`. Claude Code removes 1M model variants from the model picker. On models with a native 1M window, such as Sonnet 5 and the Fable models, it also treats the model as having a 200K context window:

609618

610619* With auto-compaction on, sessions compact at the 200K boundary through [auto-compaction](#set-the-auto-compact-window). Setting the auto-compact window above 200K doesn't lift the hold, because Claude Code caps that window at the model's context window.

611620* With auto-compaction off, sessions stop at the 200K boundary with the [context-limit error](/docs/en/errors#prompt-is-too-long) instead of compacting.

from line 671

662671

663672* [Cloud sessions](/docs/en/claude-code-on-the-web) compact as the conversation approaches the model's limit

664673* Sonnet 4.6 and Opus 4.6 without [extended context](#extended-context) compact at the 200K boundary, and so do Opus 4.8 and Opus 5 when they run with a 200K context window, such as on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry

665* When you set [`CLAUDE_CODE_DISABLE_1M_CONTEXT=1`](/docs/en/env-vars), models with a native 1M window, such as Sonnet 5 and Fable 5, compact at the 200K boundary

674* When you set [`CLAUDE_CODE_DISABLE_1M_CONTEXT=1`](/docs/en/env-vars), models with a native 1M window, such as Sonnet 5 and the Fable models, compact at the 200K boundary

666675* Sonnet 5 compacts at the [threshold for its configuration](#sonnet-5-context-window)

667676* Sessions on a model ID Claude Code doesn't recognize, such as an [LLM gateway](/docs/en/llm-gateway) alias, compact at the context window Claude Code assumes for the ID; see [Correct the window for a gateway or custom model ID](#correct-the-window-for-a-gateway-or-custom-model-id)

668677

from line 720

711720

712721| Environment variable | Description |

713722| -------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

714| `ANTHROPIC_DEFAULT_FABLE_MODEL` | The model to use for `fable`, and the model ID Claude Code recognizes as Fable 5 for [automatic model fallback](#automatic-model-fallback) on third-party providers |

723| `ANTHROPIC_DEFAULT_FABLE_MODEL` | The model to use for `fable`, and the model ID Claude Code recognizes as a Fable model for [automatic model fallback](#automatic-model-fallback) on third-party providers |

715724| `ANTHROPIC_DEFAULT_OPUS_MODEL` | The model to use for `opus`, or for `opusplan` when Plan Mode is active. |

716725| `ANTHROPIC_DEFAULT_SONNET_MODEL` | The model to use for `sonnet`, or for `opusplan` when Plan Mode is not active. |

717726| `ANTHROPIC_DEFAULT_HAIKU_MODEL` | The model to use for `haiku`, or [background functionality](/docs/en/costs#background-token-usage) |

permission-modes Changed · +3 / -3 lines

from line 280

280280

281281* **Plan**: All plans.

282282* **Organization**: on Team and Enterprise, auto mode is available by default. Administrators can turn it off for the organization by setting `permissions.disableAutoMode` to `"disable"` in [managed settings](/docs/en/managed-settings).

283* **Model**: on the Anthropic API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Claude Opus 4.6 or later, Sonnet 4.6 or later, or [Fable 5](/docs/en/model-config#work-with-fable-5). On Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and signed-in [Claude apps gateway](/docs/en/claude-apps-gateway) sessions, only Claude Sonnet 5, Opus 4.7 or later, and Fable 5. Older models, including Sonnet 4.5, Opus 4.5, Haiku, and claude-3 models, are not supported on any provider.

283* **Model**: on the Anthropic API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Claude Opus 4.6 or later, Sonnet 4.6 or later, or a [Fable model](/docs/en/model-config#work-with-fable). On Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and signed-in [Claude apps gateway](/docs/en/claude-apps-gateway) sessions, only Claude Sonnet 5, Opus 4.7 or later, and the Fable models. Older models, including Sonnet 4.5, Opus 4.5, Haiku, and claude-3 models, are not supported on any provider.

284284* **Provider**: available by default on the Anthropic API, Claude Platform on AWS, Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and signed-in Claude apps gateway sessions.

285285

286286If Claude Code reports auto mode as unavailable, first check these requirements and whether any settings file sets [`disableAutoMode`](/docs/en/settings-reference#disableautomode). Anthropic may also have turned auto mode off server-side, or the server may have rejected auto mode for your account. A session that received either answer keeps auto mode off until the session ends, so start a new session later.

from line 293

293293 Auto mode on Bedrock, Agent Platform, or Foundry

294294</h3>

295295

296On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), [Microsoft Foundry](/docs/en/microsoft-foundry), and signed-in [Claude apps gateway](/docs/en/claude-apps-gateway) sessions, auto mode appears in the `Shift+Tab` cycle by default. Appearing in the cycle doesn't change the permission mode a session starts in: on these providers, terminal sessions start in your [`defaultMode`](/docs/en/settings-reference#permissions-defaultmode), which is Manual unless you change it, and conversations in the [VS Code extension](/docs/en/vs-code) start in Manual unless `claudeCode.initialPermissionMode` or a mode you picked in the extension sets one. Only Claude Sonnet 5, Opus 4.7 or later, and Fable 5 are supported on these providers.

297297

298298To make auto mode the default starting permission mode, set `"permissions": {"defaultMode": "auto"}` in user or managed settings. In sessions the VS Code extension starts, select **Auto** from the mode indicator instead. [Switch permission modes](#switch-permission-modes) covers what outranks that pick.

299299

from line 448

448448 </Accordion>

449449

450450 <Accordion title="Cost and latency">

451 The classifier runs on Claude Sonnet 5 by default rather than on your `/model` selection. A classifier model that Anthropic configures server-side takes precedence over that default. When your session's model is Claude Sonnet 4.6, or when [`availableModels`](/docs/en/model-config#restrict-model-selection) excludes Sonnet 5, the classifier runs on the session's model instead, or on an Opus model when the session runs on [Fable 5](/docs/en/model-config#work-with-fable-5); on providers other than the Anthropic API, that Opus fallback is the provider's default Opus model.

451 The classifier runs on Claude Sonnet 5 by default rather than on your `/model` selection. A classifier model that Anthropic configures server-side takes precedence over that default. When your session's model is Claude Sonnet 4.6, or when [`availableModels`](/docs/en/model-config#restrict-model-selection) excludes Sonnet 5, the classifier runs on the session's model instead, or on an Opus model when the session runs on a [Fable model](/docs/en/model-config#work-with-fable); on providers other than the Anthropic API, that Opus fallback is the provider's default Opus model.

452452

453453 The session's first auto-mode request validates the Sonnet 5 default: if the request succeeds, Sonnet 5 stays the session's classifier model, and if it fails because the model isn't available, the session uses the fallback instead. After that validation settles, the classifier's model doesn't change for the session.

454454

settings-reference Changed · +4 / -4 lines

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

from line 814

814814

815815You don't usually edit this key by hand. Run `/advisor` to open a picker that shows the current choice, the models that can advise, and **No advisor**. Claude Code saves your pick to this key in `~/.claude/settings.json`. In a session attached to a remote worker, the pick applies to that session only.

816816

817To pick Fable, first accept the [usage-credits consent](/docs/en/advisor#fable-advisor-and-usage-credits) by running `/model fable`. Until you do, picking Fable in `/advisor` saves nothing and Claude Code tells you to run `/model fable` first.

817If your account requires the [usage-credits consent](/docs/en/advisor#fable-advisor-and-usage-credits), accept it first by running `/model fable`. Until you do, picking Fable in `/advisor` saves nothing and Claude Code tells you to run `/model fable` first.

818818

819819* **Scope**: [`Any file`](#scopes)

820820* **Type**: string, one of the aliases `"fable"`, `"opus"`, or `"sonnet"`, which resolve to Claude Code's current default version of that model family, or a full model ID such as `"claude-opus-5"`

from line 827

827827}

828828```

829829

830The key has no effect on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. `"fable"` requires [Fable 5 access](/docs/en/advisor#choose-an-advisor-model).

830The key has no effect on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. `"fable"` requires [Fable access](/docs/en/advisor#choose-an-advisor-model).

831831

832832### `alwaysThinkingEnabled`

833833

834834Turn [extended thinking](/docs/en/model-config#extended-thinking) off for every session by setting this to `false`. Thinking is on by default, so `true` changes nothing. Most people set this through `/config` rather than by editing the file.

835835

836On models that always think, such as Fable 5, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code omits the `thinking` parameter instead of turning thinking off, so adaptive-reasoning models may still think. With thinking turned off on the Anthropic API, Claude Code sends effort `high` instead of a higher level to models it knows [don't accept that combination](/docs/en/errors#effort-isnt-available-with-thinking-turned-off), such as Opus 5.

836On models that always think, such as the Fable models, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code omits the `thinking` parameter instead of turning thinking off, so adaptive-reasoning models may still think. With thinking turned off on the Anthropic API, Claude Code sends effort `high` instead of a higher level to models it knows [don't accept that combination](/docs/en/errors#effort-isnt-available-with-thinking-turned-off), such as Opus 5.

837837

838838* **Scope**: [`Any file`](#scopes)

839839* **Type**: Boolean

from line 2862

28622862

28632863### `dialogExpiry`

28642864

2865Set the deadline for dialogs Claude Code [forwards to a remote client](/docs/en/remote-control#limitations), such as a Remote Control or SDK host, for the approval dialog for a [held cross-session message](/docs/en/cross-session-messaging#control-inbound-messages), and for the mid-session [Fable 5 usage-credits consent prompt](/docs/en/model-config#fable-5-and-usage-credits) in a session that may have nobody at the terminal. When no answer arrives before the deadline, Claude Code cancels the dialog and continues with its no-action default. Requires Claude Code v2.1.224 or later.

2865Set the deadline for dialogs Claude Code [forwards to a remote client](/docs/en/remote-control#limitations), such as a Remote Control or SDK host, for the approval dialog for a [held cross-session message](/docs/en/cross-session-messaging#control-inbound-messages), and for the mid-session [Fable usage-credits consent prompt](/docs/en/model-config#fable-and-usage-credits) in a session that may have nobody at the terminal. When no answer arrives before the deadline, Claude Code cancels the dialog and continues with its no-action default. Requires Claude Code v2.1.224 or later.

28662866

28672867* **Scope**: [`User or managed`](#scopes)

28682868* **Type**: string, one of `"60s"`, `"5m"`, `"10m"`, or `"never"`, which disables the deadline

from line 3372

33723372

33733373### `verbose`

33743374

3375By default, the transcript collapses each tool call to a short summary, such as the command Claude ran and a line count of its output, and you press `Ctrl+O` to switch the whole transcript to the expanded view when you want the details. Set this key to `true` to show every tool call's full input and output inline as it happens, which is useful when you're debugging a hook, an MCP server, or a long shell command. Ap

zero-data-retention Changed · +3 / -3 lines

from line 31

3131

3232### What ZDR covers

3333

34ZDR covers model inference calls made through Claude Code on Claude for Enterprise. When you use Claude Code in your terminal, the prompts you send and the responses Claude generates are not retained by Anthropic. This applies to every model available to ZDR organizations. Some models require data retention and are not available under ZDR; see [Model availability under ZDR](#model-availability-under-zdr).

34ZDR covers model inference calls made through Claude Code on Claude for Enterprise. When you use Claude Code in your terminal, the prompts you send and the responses Claude generates are not retained by Anthropic. This applies to every model available to your ZDR organization. Some models require data retention by default; see [Model availability under ZDR](#model-availability-under-zdr).

3535

3636### What ZDR does not cover

3737

from line 64

6464

6565### Model availability under ZDR

6666

67Claude Fable 5 is not available for organizations with zero data retention enabled. This model class [requires data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements), so requests from ZDR organizations cannot be served by it. The model is either absent from the `/model` picker for ZDR organizations or shown as disabled with a notice that disabling ZDR is required, and the server rejects requests for it regardless of client configuration.

67Claude Fable 5.1 and Fable 5 are [Covered Models](https://support.claude.com/en/articles/15425695-covered-models) that [require data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements) by default, and whether a ZDR organization or workspace can use them is governed by the Covered Models policies rather than by Claude Code. Where your organization can't use them, the models are either absent from the `/model` picker or shown as disabled, and the server rejects requests for them regardless of client configuration.

6868

69Other models remain available under ZDR. Fable 5 is not the default model, and the `best` alias, which resolves to Fable 5 where it is available, resolves to Opus for organizations where it is not, including ZDR organizations.

69Other models remain available under ZDR. Fable models are not the default, and the `best` alias, which resolves to the latest Fable model where it is available, resolves to Opus for organizations where it is not.

7070

7171## Data retention for policy violations

7272

claude-security Changed · +1 / -1 lines

from line 134

134134

135135**The `/claude-security` menu opens with a Python warning.** The plugin needs `python3` 3.9 or later on your `PATH`. When it can't find `python3` at all, the menu warns that Claude Security won't work until one is installed; when the first `python3` on your `PATH` is older, the warning names the version it found. Install Python 3, or put a newer `python3` first on your `PATH`, then start a new session.

136136

137**You may see "Fable 5's safeguards flagged this message" when using Fable 5.** Due to Fable 5's cybersecurity safety classifiers, certain model activities will be blocked and automatically downgraded to Opus. This is expected, and the scan should still complete successfully.

137**You may see "Fable 5.1's safeguards flagged this message" or "Fable 5's safeguards flagged this message" when using a Fable model.** Due to Fable's cybersecurity safety classifiers, certain model activities will be blocked and automatically downgraded to Opus. This is expected, and the scan should still complete successfully.

138138

139139## Related resources

140140

cli-reference Changed · +2 / -2 lines

from line 54

5454| Flag | Description | Example |

5555| :---------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------- |

5656| `--add-dir` | Add additional working directories for Claude to read and edit files. Grants file access; most `.claude/` configuration is [not discovered](/docs/en/permissions#additional-directories-grant-file-access-not-configuration) from these directories. Validates each path exists as a directory. To persist these directories across sessions, set [`permissions.additionalDirectories`](/docs/en/settings-reference#permissions-additionaldirectories) in settings | `claude --add-dir ../apps ../lib` |

57| `--advisor <model>` | Enable the server-side [advisor tool](/docs/en/advisor) for this session with a model alias, `fable`, `opus`, or `sonnet`, or a full model ID. Takes precedence over the `advisorModel` setting for the session. `fable` requires [Fable 5 access](/docs/en/advisor#choose-an-advisor-model) | `claude --advisor opus` |

57| `--advisor <model>` | Enable the server-side [advisor tool](/docs/en/advisor) for this session with a model alias, `fable`, `opus`, or `sonnet`, or a full model ID. Takes precedence over the `advisorModel` setting for the session. `fable` requires [Fable access](/docs/en/advisor#choose-an-advisor-model) | `claude --advisor opus` |

5858| `--agent` | Specify an agent for the current session (overrides the `agent` setting) | `claude --agent my-custom-agent` |

5959| `--agents` | Define custom subagents dynamically via JSON. Accepts the [fields listed for CLI-defined subagents](/docs/en/sub-agents#choose-the-subagent-scope). Claude Code validates the JSON at startup and exits on an invalid value; see [`Invalid --agents configuration`](/docs/en/errors#invalid-agents-configuration) for the message and for the flags and environment variable that skip the validation. Validation requires Claude Code v2.1.242 or later | `claude --agents '{"reviewer":{"description":"Reviews code","prompt":"You are a code reviewer"}}'` |

6060| `--allow-dangerously-skip-permissions` | Add `bypassPermissions` to the `Shift+Tab` mode cycle without starting in it. Lets you begin in a different mode like `plan` and switch to `bypassPermissions` later. See [permission modes](/docs/en/permission-modes#skip-all-checks-with-bypasspermissions-mode) | `claude --permission-mode plan --allow-dangerously-skip-permissions` |

from line 97

9797| `--max-budget-usd` | Maximum dollar amount to spend on API calls before stopping (print mode only). Spend from [subagents](/docs/en/sub-agents) counts toward the cap. Once spend reaches the cap, spawning another subagent fails with `Budget limit reached`, and Claude Code stops background subagents that are still running; the cap-enforcement behaviors require Claude Code v2.1.217 or later | `claude -p --max-budget-usd 5.00 "query"` |

9898| `--max-turns` | Limit the number of agentic turns (print mode only). Exits with an error when the limit is reached. No limit by default. With `--input-format stream-json`, a message still queued when the limit ends a turn stays queued and starts a new turn with its own limit | `claude -p --max-turns 3 "query"` |

9999| `--mcp-config` | Load MCP servers from JSON files or strings (space-separated). When you pass this flag with `-p`, Claude Code waits for still-pending servers to connect before running the first turn, up to the [`MCP_TIMEOUT`](/docs/en/env-vars) startup timeout, 30 seconds by default; a server with a [cached tool list](/docs/en/mcp#managing-your-servers) skips the wait and connects on first use. The wait requires Claude Code v2.1.221 or later | `claude --mcp-config ./mcp.json` |

100| `--model` | Sets the model for the current session with an alias for the latest model (`sonnet`, `opus`, `haiku`, or `fable`) or a model's full name. Overrides the [`model`](/docs/en/settings-reference#model) setting and [`ANTHROPIC_MODEL`](/docs/en/model-config#environment-variables) | `claude --model claude-sonnet-5` |

100| `--model` | Sets the model for the current session with a [model alias](/docs/en/model-config#model-aliases) such as `sonnet`, `opus`, `haiku`, or `fable`, or a model's full name. Overrides the [`model`](/docs/en/settings-reference#model) setting and [`ANTHROPIC_MODEL`](/docs/en/model-config#environment-variables) | `claude --model claude-sonnet-5` |

101101| `--name`, `-n` | Set a display name for the session, shown in `/resume` and the terminal title. You can resume a named session with `claude --resume <name>`. In an interactive session, if another live session on this machine already uses the name, Claude Code applies [a variant of it](/docs/en/sessions#name-your-sessions) instead. [`/rename`](/docs/en/commands) changes the name mid-session and also shows it on the prompt bar | `claude -n "my-feature-work"` |

102102| `--no-chrome` | Disable [Chrome browser integration](/docs/en/chrome) for this session | `claude --no-chrome` |

103103| `--no-session-persistence` | Disable session persistence so sessions are not saved to disk and cannot be resumed. Print mode only. The [`CLAUDE_CODE_SKIP_PROMPT_HISTORY`](/docs/en/env-vars) environment variable does the same in any mode | `claude -p --no-session-persistence "query"` |

commands Changed · +1 / -1 lines

from line 46

4646| Command | Purpose |

4747| :-------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

4848| `/add-dir <path>` | Add a working directory for file access during the current session. Type a partial path to see matching directory suggestions; press `Tab` to accept one. Most `.claude/` configuration is [not discovered](/docs/en/permissions#additional-directories-grant-file-access-not-configuration) from the added directory. A successful add runs your [`DirectoryAdded` hooks](/docs/en/hooks#directoryadded). When you run it while Claude is responding, Claude Code asks you to confirm the directory right away, and once you confirm, Claude's next tool call in the same turn can access it. Before v2.1.234, Claude Code queued the command until the turn finished |

49| `/advisor [model\|off]` | Enable or disable the [advisor tool](/docs/en/advisor), which consults a second model for guidance at key moments during a task. Accepts `fable`, `opus`, `sonnet`, or a full model ID. `fable` requires [Fable 5 access](/docs/en/advisor#choose-an-advisor-model). Without an argument, opens a picker |

49| `/advisor [model\|off]` | Enable or disable the [advisor tool](/docs/en/advisor), which consults a second model for guidance at key moments during a task. Accepts `fable`, `opus`, `sonnet`, or a full model ID. `fable` requires [Fable access](/docs/en/advisor#choose-an-advisor-model). Without an argument, opens a picker |

5050| `/agents` | As of v2.1.198, running `/agents` prints a reminder to ask Claude to create or manage [subagents](/docs/en/sub-agents), or to edit `.claude/agents/` or `~/.claude/agents/` directly. On v2.1.197 and earlier, opens an interactive interface for creating and managing subagent configurations |

5151| `/artifacts` | List the [artifacts](/docs/en/artifacts#find-an-artifact-again) you own or that are shared with you, then attach one to the session, open it in your browser, or copy its link. Available where [artifacts](/docs/en/artifacts#availability) are. Requires Claude Code v2.1.208 or later; attaching with `Enter` requires v2.1.216 |

5252| `/auto-mode-setup` | [Draft `autoMode.environment` entries](/docs/en/auto-mode-config#generate-environment-entries) from your project and recent sessions, then review the draft and save it to your user settings. Requires a Pro, Max, or Team plan and Claude Code v2.1.228 or later. On native Windows, requires v2.1.233 or later |

context-window Changed · +1 / -1 lines

from line 1620

16201620* **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.

16211621* **Delegate large reads**: send research to a [subagent](/docs/en/sub-agents) so the file contents stay in its context window, not yours.

16221622

1623If you need a larger window rather than a smaller conversation, Fable 5, Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Extended context](/docs/en/model-config#extended-context) for availability by plan and how to select a `[1m]` model variant. Sonnet 5 runs at 1M with no `[1m]` variant to select; see [Sonnet 5 context window](/docs/en/model-config#sonnet-5-context-window) for its auto-compaction thresholds and the LLM gateway exception. Compaction works the same way at the larger limit.

1623If you need a larger window rather than a smaller conversation, Fable 5.1, Fable 5, Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Extended context](/docs/en/model-config#extended-context) for availability by plan and how to select a `[1m]` model variant. Sonnet 5 runs at 1M with no `[1m]` variant to select; see [Sonnet 5 context window](/docs/en/model-config#sonnet-5-context-window) for its auto-compaction thresholds and the LLM gateway exception. Compaction works the same way at the larger limit.

16241624

16251625The point where automatic compaction runs depends on your model and configuration. See [Default auto-compact thresholds](/docs/en/model-config#default-auto-compact-thresholds) for the boundaries per model, and [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id) if Claude Code assumes the wrong window for your model ID, such as an [LLM gateway](/docs/en/llm-gateway) alias.

16261626

costs Changed · +1 / -1 lines

from line 304

304304

305305### Adjust extended thinking

306306

307Extended thinking is enabled by default because it significantly improves performance on complex planning and reasoning tasks. Thinking tokens are billed as output tokens, and the default budget can be tens of thousands of tokens per request depending on the model. For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, disabling thinking in `/config`, or, on models with a [fixed thinking budget](/docs/en/model-config#adaptive-reasoning-and-fixed-thinking-budgets), lowering the budget by setting the `MAX_THINKING_TOKENS` [environment variable](/docs/en/env-vars), for example `MAX_THINKING_TOKENS=8000`. Adaptive-reasoning models ignore nonzero budgets, so use effort levels there instead. Disabling thinking is not available on Fable 5, which always uses extended thinking.

308308

309309### Delegate verbose operations to subagents

310310

glossary Changed · +1 / -1 lines

from line 128

128128

129129### Effort level

130130

131A setting that controls how much of the adaptive-reasoning thinking budget Claude uses on each turn. Higher effort means more thinking tokens and deeper reasoning; lower effort is faster and cheaper. Effort is supported on Fable 5, on Opus 4.6 and later, and on Sonnet 4.6 and later.

131A setting that controls how much of the adaptive-reasoning thinking budget Claude uses on each turn. Higher effort means more thinking tokens and deeper reasoning; lower effort is faster and cheaper. Effort is supported on Fable 5.1 and Fable 5, on Opus 4.6 and later, and on Sonnet 4.6 and later.

132132

133133Learn more: [Adjust effort level](/docs/en/model-config#adjust-effort-level)

134134

interactive-mode Changed · +1 / -1 lines

from line 33

3333| `Esc` + `Esc` | Clear input draft, or rewind | When the prompt input contains text, double `Esc` clears it and saves the draft to history so `Up` recalls it. When the input is empty, double `Esc` opens the [rewind menu](/docs/en/checkpointing) to restore or summarize code and conversation from a previous point |

3434| `Shift+Tab`, or `Alt+M` on Windows when the Node or Bun runtime doesn't enable VT input mode | Cycle permission modes | Cycle through `default` (labeled Manual in the mode indicator), `acceptEdits`, `plan`, and, when available, `bypassPermissions` and then `auto`. From `auto`, the first press switches to `default`. See [permission modes](/docs/en/permission-modes). On a file permission prompt, the same key closes an open [comment field](/docs/en/permissions#add-a-comment-when-you-answer-a-permission-prompt). With no field open, it selects the option that allows the action for the rest of the session, when the prompt offers that option |

3535| `Option+P` (macOS) or `Alt+P` (Windows/Linux) | Switch model | Switch models without clearing your prompt |

36| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking | Enable or disable extended thinking mode. Has no effect on Fable 5, which always uses extended thinking. Works on macOS without configuring Option as Meta |

36| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking | Enable or disable extended thinking mode. Has no effect on Fable 5.1 or Fable 5, which always use extended thinking. Works on macOS without configuring Option as Meta |

3737| `Option+O` (macOS) or `Alt+O` (Windows/Linux) | Toggle fast mode | Enable or disable [fast mode](/docs/en/fast-mode) |

3838

3939### Text editing

llm-gateway-protocol Changed · +1 / -1 lines

from line 195

195195

196196The picker is the interactive model list that opens when a developer runs `/model` in Claude Code. Each discovered entry is labeled "From gateway" and uses `display_name` when provided. The [`availableModels` managed setting](/docs/en/settings-reference#availablemodels) bounds what discovery can add.

197197

198A discovered ID is skipped when it exactly matches a row already in the picker, or when both the discovered and existing IDs resolve to [Fable](/docs/en/model-config#work-with-fable-5). A discovered explicit ID is also folded into a built-in entry when both resolve to the same model. Built-in rows are keyed on aliases such as `sonnet`, so a discovered explicit ID of the model the alias currently resolves to, such as `claude-sonnet-5`, collapses into the `sonnet` row, while an ID the alias doesn't resolve to, such as `claude-sonnet-4-6`, still adds its own "From gateway" row alongside the built-in entry. Before v2.1.197, Claude Code didn't fold explicit IDs into built-in entries, so a discovered ID such as `claude-sonnet-5` added its own "From gateway" row alongside the `sonnet` row.

198A discovered ID is skipped when it exactly matches a row already in the picker, or when the discovered and existing IDs are spellings of the same [Fable](/docs/en/model-config#work-with-fable) version. A discovered explicit ID is also folded into a built-in entry when both resolve to the same model. Built-in rows are keyed on aliases such as `sonnet`, so a discovered explicit ID of the model the alias currently resolves to, such as `claude-sonnet-5`, collapses into the `sonnet` row, while an ID the alias doesn't resolve to, such as `claude-sonnet-4-6`, still adds its own "From gateway" row alongside the built-in entry. Before v2.1.197, Claude Code didn't fold explicit IDs into built-in entries, so a discovered ID such as `claude-sonnet-5` added its own "From gateway" row alongside the `sonnet` row.

199199

200200Results are cached to `~/.claude/cache/gateway-models.json`, or `%USERPROFILE%\.claude\cache\gateway-models.json` on Windows, and refreshed on each startup. If you set [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars), the cache lives under that directory instead. If the request fails or the gateway doesn't implement `/v1/models`, the picker falls back to the cached list from the previous startup or to the built-in model list. If your gateway serves Claude models under aliases that don't match the discovery filter, developers can add those aliases manually with the [model configuration](/docs/en/model-config) variables.

201201

prompt-caching Changed · +1 / -1 lines

from line 83

8383

8484The [`opusplan` model setting](/docs/en/model-config#opusplan-model-setting) resolves to Opus during plan mode and Sonnet during execution, so each plan-mode toggle is a model switch and starts a fresh cache.

8585

86[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable 5 and Opus 5 is also a model switch. When a safety classifier flags a request and the flagged category has a fallback model, Claude Code re-runs the request on that model and the session continues there.

86[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable 5.1, Fable 5, and Opus 5 is also a model switch. When a safety classifier flags a request and the flagged category has a fallback model, Claude Code re-runs the request on that model and the session continues there.

8787

8888### Changing effort level

8989

remote-control Changed · +1 / -1 lines

from line 323

323323 * **Server mode**: Claude Code gives up after roughly 10 minutes and the `claude remote-control` process exits. Run `claude remote-control` again to start a new session.

324324 * **Interactive session**: keep working locally. Claude Code retries for as long as the outage lasts and reconnects on its own when the network returns.

325325* **Presence heartbeats failing**: if an interactive session disconnects with `could not reach the Remote Control server for about 30 minutes`, run `/remote-control` to reconnect. Claude Code shows this message only when the session's presence heartbeats have been failing while the rest of the connection stayed up; it re-registers the session for about 30 minutes before disconnecting.

326* **Forwarded dialogs expire**: Claude Code keeps permission prompts and `AskUserQuestion` questions open until you answer them. When Claude Code forwards another kind of dialog to the remote session, such as the model-choice prompt shown after a safety refusal, it waits five minutes by default, then closes the dialog and continues with the dialog's no-action default. The mid-session [Fable 5 usage-credits consent prompt](/docs/en/model-config#fable-5-and-usage-credits) follows the same deadline but isn't forwarded: Claude Code shows it only in the terminal where the session runs, and if nobody has answered there by the deadline, it ends the turn without sending the request. Your model selection is unchanged, and Claude Code asks again on your next message. Set [`dialogExpiry`](/docs/en/settings-reference#dialogexpiry) to adjust or disable the deadline. Requires Claude Code v2.1.224 or later. Claude Code applies the same deadline to the approval dialog for a held cross-session message. [The held-message expiry rules](/docs/en/cross-session-messaging#control-inbound-messages) cover the cases where Claude Code keeps the dialog open past it.

326* **Forwarded dialogs expire**: Claude Code keeps permission prompts and `AskUserQuestion` questions open until you answer them. When Claude Code forwards another kind of dialog to the remote session, such as the model-choice prompt shown after a safety refusal, it waits five minutes by default, then closes the dialog and continues with the dialog's no-action default. The mid-session [Fable usage-credits consent prompt](/docs/en/model-config#fable-and-usage-credits) follows the same deadline but isn't forwarded: Claude Code shows it only in the terminal where the session runs, and if nobody has answered there by the deadline, it ends the turn without sending the request. Your model selection is unchanged, and Claude Code asks again on your next message. Set [`dialogExpiry`](/docs/en/settings-reference#dialogexpiry) to adjust or disable the deadline. Requires Claude Code v2.1.224 or later. Claude Code applies the same deadline to the approval dialog for a held cross-session message. [The held-message expiry rules](/docs/en/cross-session-messaging#control-inbound-messages) cover the cases where Claude Code keeps the dialog open past it.

327327* **Some commands are local-only**: commands that only run in the terminal interface, such as `/plugin` or `/resume`, work only from the local CLI, whether or not you pass an argument. The following work from mobile and web:

328328 * Text-output commands: `/compact`, `/clear`, `/context`, `/usage`, `/exit`, `/usage-credits` (prints the billing URL instead of opening a browser), `/recap`, `/reload-plugins`

329329 * `/model`, `/effort`, `/fast`, `/color`, and `/rename`: pass the value as an argument, for example `/model sonnet` or `/effort high`. From mobile and web, `/model` and `/effort` take the argument in place of the terminal picker or slider.

vs-code Changed · +1 / -1 lines

from line 371

371371* **Claude's replies**: the extension announces each reply once, when it's complete, and stays silent while text streams in. Your screen reader reads code blocks as a line-count summary, reads links by their label, and reads tables cell by cell; the full reply stays readable in the transcript.

372372* **Permission requests and questions**: the extension announces a request when its permission prompt appears, naming the tool Claude wants to use. It announces in the same way when Claude asks you a question and when Claude finishes a plan and waits for your review.

373373* **Status changes**: the extension announces when Claude starts working, when Claude is ready for your input, and when Claude Code starts compacting the conversation.

374* **Errors and model prompts**: the extension announces errors in the conversation, and announces when the [usage-credits consent prompt](/docs/en/model-config#fable-5-and-usage-credits) or the [flagged-request prompt](/docs/en/model-config#ask-before-switching) appears.

374* **Errors and model prompts**: the extension announces errors in the conversation, and announces when the [usage-credits consent prompt](/docs/en/model-config#fable-and-usage-credits) or the [flagged-request prompt](/docs/en/model-config#ask-before-switching) appears.

375375

376376Each turn in the transcript starts with a visually hidden heading labeled with the prompt that started the turn, so you can jump between turns with your screen reader's heading navigation. You can also move focus to the transcript itself with `Tab`, since the extension exposes it as a labeled region, and read it at your own pace. While Claude works, your screen reader reads a text label in place of the progress spinner's animation.

377377

One read of Claude Code CLI

What this read moved

advisor Changed · +23 / -23 lines

changelog Changed · +107 / -0 lines

communications-kit Changed · +7 / -7 lines

desktop Changed · +4 / -4 lines

env-vars Changed · +8 / -7 lines

errors Changed · +24 / -8 lines

feature-availability Changed · +4 / -4 lines

model-config Changed · +60 / -51 lines

permission-modes Changed · +3 / -3 lines

settings-reference Changed · +4 / -4 lines

zero-data-retention Changed · +3 / -3 lines

claude-security Changed · +1 / -1 lines

cli-reference Changed · +2 / -2 lines

commands Changed · +1 / -1 lines

context-window Changed · +1 / -1 lines

costs Changed · +1 / -1 lines

glossary Changed · +1 / -1 lines

interactive-mode Changed · +1 / -1 lines

llm-gateway-protocol Changed · +1 / -1 lines

prompt-caching Changed · +1 / -1 lines

remote-control Changed · +1 / -1 lines

vs-code Changed · +1 / -1 lines