Home Docs Claude Code CLI

One capture · claude-code

One read of Claude Code CLIclaude-code-20261019T220701Z

11 pages moved out of 228 read.

Pages moved 11 significant first

Pages read 228 in this capture

Captured 19 Oct 2026 22:07 UTC

Corpus hash 55c8e39f1150 corpus-hash

What this read moved

1-11 of 11

changelog Changed · +90 / -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="2.1.304" description="October 19, 2026">

10 **Added**

12 * Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin

13 * Added `decider: "person"` to a mod's `tool.check` answer: only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be asked

14 * Added `e.isReadOnly` to a mod's `tool.check` event, set when the tool call is read-only

15 * Added `/auto-mode-setup`: a guided setup that reads your project and recent sessions to teach auto mode about your environment, now also available on Bedrock, Vertex, Foundry, Claude apps gateway and telemetry-disabled sessions

16 * Added `/claude-api managed-agents-secure`, which compares a Managed Agents agent's settings with Anthropic's published security guide, without changing anything

17 * Added the names of the tools called earlier to the compaction summary in the transcript view (Ctrl+O)

18 * Added a warning on Pro and Max plans when resuming an inactive conversation would use a noticeable share of your 5-hour usage limit: resume anyway, or start a new conversation and Claude can look up the previous one if you refer to it

19 * \[VSCode] Added mod drawing in the chat panel for sessions on Amazon Bedrock, Google Vertex AI and Microsoft Foundry, behind an LLM gateway, or with telemetry turned off

20 * \[Code Review] Added review levels to Code Review: Owners choose Quick, Standard (the default), or Deep for the organization, and can give individual repositories their own level

21 * \[Code Review] Added an option in Code Review admin settings to review every repository in a GitHub organization, including ones added later, without selecting them one by one

23 **Changed**

25 * Changed mods' `settings.read` hooks to receive each settings layer and rewrite the merged settings, so a managed mod can make an organization's setting a ceiling, including the `cleanupPeriodDays` the retention sweep uses

26 * Changed the `/artifacts` delete confirmation to show numbered choices: 1 or Enter keeps the artifact, 2 deletes it, and y, n and Esc still work

27 * Changed the question that turns on the mods Claude writes in a session to plain text with no link or session id; it stays up when a new turn starts, and Claude tells you what loaded when you turn them on

28 * Changed tool search to be on by default behind a custom `ANTHROPIC_BASE_URL`; a 400 or 422 from the gateway is retried without it

29 * Changed compaction to send Claude the skill list again afterwards; `/reload-skills` now sends only new or changed skills

30 * Changed skill hooks: the skills of one source (a repo, your own folder, or a plugin) can register at most 1,024 hooks and 16,384 matcher characters per session

31 * Changed skills under a policy that allows hooks from plugins only: a skill used in the main conversation whose hooks are kept out no longer gets its `allowed-tools`

32 * Updated the /claude-api skill to use the `ant` CLI on Claude Platform on AWS instead of falling back to the SDK or curl

33 * Removed the notes from `claude plugin validate` that predicted where a mod's hooks would run

34 * Removed the "(research preview)" label from the `/fast` dialog title on Opus 5.5

35 * \[VSCode] Changed background sub-agents to show as one status line under their Agent card instead of streaming every step into the chat; the full transcript stays in /tasks

37 <Expandable title="12 improvements">

38 - Improved `/usage` to say when a rate limit on usage data ends instead of "try again in a moment"

39 - Improved the lines shown when a mod written in the session loads, reloads or fails to load

40 - Improved artifacts with several views: when you ask for links to them, Claude now writes out each view's link and explains that the address bar stays the same as you switch views

41 - Improved cloud sessions: a new conversation's first turn no longer waits for the local (stdio) MCP servers of plugins synced from claude.ai, unless a server sets `alwaysLoad: true`

42 - Improved how a remote session recovers its status when the server refuses a status update that carried other session data

43 - Improved session file size in auto mode: the safety classifier's context is no longer stored with every request

44 - Improved the `claude -p` invalid-settings warning: a file that did not load lists only what stopped it, and long lists are capped per file

45 - Improved resume of large compacted sessions in SDK and headless mode: the first request after resuming is sent sooner

46 - Improved responsiveness and throughput when many subagents are running at the same time

47 - Improved memory use when sending requests in long or resumed conversations

48 - Self-hosted runner: Improved the error shown when the git host answers "not found" for a session's repository: it now names the repository and whom to ask

49 - Windows: Improved git command start-up with a standard Git for Windows install by running its git.exe directly instead of through its cmd launcher

50 </Expandable>

52 <Expandable title="43 bug fixes">

53 * Fixed the organization policy not refreshing until the hourly check after approving an `ANTHROPIC_API_KEY` at startup or switching "Use custom API key" in `/config`

54 * Fixed sandboxed commands failing to start on Linux when a `sandbox.filesystem.denyRead` glob contains brackets that are not a character class, such as a `[user-id]` route folder

55 * Fixed `rm -r` of a mounted drive or a folder at its top level (`/Volumes`, `/media`, WSL's `/mnt/c`) not getting the safety prompt that `rm -rf /Applications` gets

56 * Fixed `CLAUDE_CODE_TRANSCRIPT_LOCAL_GC` dropping messages from the saved transcript when the disk filled up while the file was being trimmed

57 * Fixed a plugin keeping a headless run going past `--max-turns`, Stop, or ended input by spawning subagents or re-running a finished one

58 * Fixed a failed mod reload removing the tools and commands of the version that stays loaded, and its messages being wrong or silent about whether the previous version is still loaded

59 * Fixed a click on a mod's button being lost when buttons with the same label and no `key` were redrawn unchanged

60 * Fixed mod sharing in the built-in `plugin-authoring` skill stopping at the secret scan on machines with managed settings and on Team and Enterprise plans

61 * Fixed scheduled Cowork cloud sessions waiting five minutes again for each subagent whose WebFetch needed a URL approval that nobody was there to give

62 * Fixed Write results and rejected edits showing a file outside the working directory as `../../…`; they now show `~/…` or the full path

63 * Fixed a claude.ai Directory plugin's skills not running as commands when picked from the "/" menu in Cowork cloud sessions

64 * Fixed Remote Control permanently withholding a desktop conversation's history when a different account was signed in to the terminal

65 * Fixed Remote Control failing to start from Claude Desktop when DISABLE\_TELEMETRY or DO\_NOT\_TRACK is set on a paid plan

66 * Fixed model switches, messages and interrupts waiting behind a context usage check in SDK and desktop sessions

67 * Fixed `context_management: Extra inputs are not permitted` errors behind LLM gateways; Claude Code now resends the request without that field

68 * Fixed OpenTelemetry settings delivered through server-managed settings being ignored for the whole session after signing in during first-run setup or the first start after /logout

69 * Fixed unsandboxed Bash commands in Claude Desktop Code tab sessions on macOS and Linux not seeing environment variables exported in shell startup files such as \~/.zshrc

70 * Fixed the Consumer Terms notice being skipped for a day or longer after a server error

71 * Fixed `/privacy-settings` offering choices that may not apply to you after a network or server error

72 * Fixed a "Context limit reached" or "Prompt is too long" error after stopping a turn while Claude Code was compacting a conversation the API had rejected as too long

73 * Fixed subagents sometimes forgetting their most recent work when they were messaged or resumed right after finishing

74 * Fixed `claude --help` text for `--tools`, `--resume`, `--debug`, `--json-schema`, `--disable-slash-commands`, `--system-prompt-snapshot` and `claude update` to match actual behavior

75 * Fixed `claude --worktree` removing the worktree and its branch without asking at exit when HEAD was detached or on another branch, which could lose commits

76 * Fixed resumed and cloud sessions sending Claude the whole skill list again each time plugins reloaded at startup

77 * Fixed an interrupt not ending a Read that waits on an idle pipe or device named like an image

78 * Fixed `/effort status`, `/effort ultracode` and the prompt's effort indicator showing a guessed effort level when `CLAUDE_CODE_EFFORT_LEVEL` is `auto` or `unset` and no level is sent

79 * Fixed a PreToolUse hook's deny reason being replaced by a timeout error when an Agent SDK callback hook on the same tool call timed out

80 * Fixed Bash and PowerShell deleting a large command's output file when it could not be copied to the session's tool-results folder, unless the disk is full

81 * Fixed notes typed into a multiple-choice question with previews being cut off with "…" in terminals under about 100 columns, hiding what was typed (anthropics/claude-code#82768)

82 * Fixed self-paced `/loop` wakeups scheduled at the 1-hour maximum firing just after the 1-hour prompt cache expired, so those wakeups no longer re-read the conversation uncached

83 * Fixed agent teams: approving a shutdown request from the main session no longer exits the whole CLI

84 * Fixed a skill's `once` hook also removing another skill's identical hook after it ran

85 * Fixed transcript mode's `{` and `}` landing the prompt on an inconsistent row, or off screen, instead of the transcript's first row

86 * Fixed `CLAUDE_CODE_AUTO_COMPACT_WINDOW=200k` silently setting a 100K window: the variable now accepts `k` and `M` suffixes like `--autocompact`, and warns when a value is out of range or ignored

87 * Fixed Ctrl+C in the agents view clearing a text selection without copying it when pressed before the mouse button was released

88 * \[VSCode] Fixed one cause of sessions failing to start with "Subprocess initialization did not complete within 60000ms": time a SessionStart command hook spends running no longer counts toward the limit, up to 10 minutes in total

89 * \[VSCode] Fixed a session closed while it was starting keeping its Claude Code process running until the start ended

90 * \[VSCode] Fixed a mod's drawings disappearing from a long-open panel until the next turn on machines that also run an older Claude Code

91 * \[VSCode] Fixed Past conversations hiding sessions when `claudeCode.claudeProcessWrapper` is set

92 * \[Cloud sessions] Fixed folders in the composer's @ list showing no name in cloud sessions, where picking one added only a space instead of a mention

93 * \[Claude Tag] Fixed Claude going silent in a thread when its channel becomes shared across Enterprise Grid workspaces mid-task; it now posts a one-time note to @-mention it in a new thread

94 * \[Claude Tag] Fixed `@Claude !fork` typed outside a thread getting no visible reply; Claude now shows you a private note saying to run it from inside a thread

95 * \[Code Review] Fixed pull requests opened within a minute or two of an admin turning on Code Review being silently skipped; they are now retried and reviewed

96 </Expandable>

97</Update>

999<Update label="2.1.303" description="October 18, 2026">

10100 * Bug fixes and reliability improvements

11101</Update>

from line 1940

18501940

18511941 **Changed**

18521942

1853 * Updated the `claude-api` skill: pre-output refusal billing now links to the How refusals are billed docs, mid-stream refusals bill at normal rates, and pre-output refusals count against rate limits

1854 * Updated the `claude-api` skill to recommend `ant apply` for keeping Managed Agents resources as version-controlled files

1855 * Changed auto mode to use the server-side classifier by default on a direct Anthropic API connection when telemetry is off (`CLAUDE_CODE_AUTO_MODE_SERVER=0` opts out)

1856 * Changed `sandbox.excludedCommands` to ignore project and local settings entries when managed settings or `--settings` set `allowUnsandboxedCommands: false`, or managed `allowManagedDomainsOnly: true`

1857 * Changed project and local settings to ignore OpenTelemetry variables that turn on export, set its endpoint, or capture content, like `CLAUDE_CODE_ENABLE_TELEMETRY` and `OTEL_LOG_*`

1858 * Changed Windows/WSL managed settings so an admin policy that is present but invalid or unreadable (HKLM, `managed-settings.json`) keeps user-writable HKCU and WSL `/etc/claude-code` from applying

1859 * Changed `Skill(anthropic-skills:*)` and `Skill(claude-ai:*)` allow rules to cover only skills synced from claude.ai, not plugins or other skills that merely use such a name

1860 * Changed skill folders, command files and workflow commands in the `anthropic-skills` or `claude-ai` namespace to no longer load; a plugin so named still loads but yields name ties to synced skills

1861 * Changed MCP servers configured under the name `anthropic-skills` or `claude-ai` to list no skills or prompts (their tools still work); rename the server in your MCP configuration to list them again

1862 * Changed the `ultracode` visuals in `/effort` and the prompt input to plain styling (no ripple, border flourish or keyword glimmer) and removed the dynamic-workflows spinner tip

1863 * Changed the Clawd mascot's feet in the start-up banner to sit under the corners of his body

1864 * \[Claude Tag] Changed the bordered cards Claude uses in Slack replies for plans, tables and details to render wide by default instead of a narrow width

1865 * \[Claude Tag] Changed newly connected Slack workspaces to follow the current default model instead of keeping whichever model was the default when they were connected

1866

1867 <Expandable title="6 improvements">

1868 - Improved the time to resume very large sessions, including ones that were never compacted

1869 - Improved the error shown on Windows when a session can't be resumed because its transcript file could not be read (EBADF): it now names possible causes and what to try

1870 - Improved the Claude Desktop unknown-model error to suggest switching to a different model

1871 - Improved rendering of unusual Unicode in permission prompts

1872 - Improved `/artifacts`: titles line up in one column, details are dropped whole instead of cut mid-word, and the list supports PgUp/PgDn, Home/End, the mouse wheel and clicks

1873 - \[Cloud sessions] Improved how quickly the Routines page and the sidebar's Scheduled list load for accounts whose past sessions scheduled many check-in reminders

1874 </Expandable>

1875

1876 <Expandable title="59 bug fixes">

1877 * Fixed every request failing with a 400 error in conversations whose history holds web search results the API cannot decrypt (for example, from a turn answered through a third-party gateway)

1878 * Fixed more cases of continued or resumed sessions (`--continue`, `--resume`) re-sending earlier messages in a changed form, which could make the API drop Claude's earlier reasoning

1879 * Fixed earlier extended thinking being dropped when `/model`, `/rename`, `/artifacts` or another immediate slash command was used while Claude was working

1880 * Fixed continued or resumed conversations losing earlier extended thinking when relaunched with a `--tools` list that leaves out a built-in tool offered earlier in the conversation

1881 * Fixed sessions failing on every turn with an "Invalid `data` in `redacted_thinking` block" API error; Claude Code now drops the conversation's thinking blocks and retries once

1882 * Fixed compaction failing when the summarization request is refused; it now retries on a fallback model

1883 * Fixed a failed turn ("Effort 'xhigh' isn't available with thinking turned off") after a safety-related model switch in sessions with thinking off and effort above high

1884 * Fixed an unanswered Fable usage-credits prompt switching models in SDK-hosted sessions such as Claude Desktop; the turn now ends instead, and Remote Control clients now see the model-switch notice

1885 * Fixed `/model` with a full Fable model id stopping at an API error instead of opening the usage-credits prompt when the plan needs usage credits that aren't turned on yet

1886 * Fixed requests failing for up to a minute with an "another Claude Code process is refreshing it" login error after that other process was closed or killed mid-refresh

1887 * Fixed sessions started while another Claude Code window was refreshing the sign-in (common with several VS Code windows) not retrying their organization policy fetch

1888 * Fixed CLAUDE.md and rules being read at startup through a repository symlink reaching macOS's `/Network` via `..` or a `/.vol`-style kernel path, or a rules link to macOS's `/home` being listed

1889 * Fixed Bash permission rules with a mid-pattern `:*` being skipped in settings files while `--allowedTools` honored them; they now work from every source, with a startup warning on how they match

1890 * Fixed a command approved on a restored permission prompt running twice when a remote session's worker restarted

1891 * Fixed managed settings ignoring a mistyped value for boolean lock keys such as `disableClaudeAiConnectors` or `allowManagedPermissionRulesOnly`; the lock now applies and startup names the key

1892 * Fixed managed `permissions`, `autoMode`, `worktree` and `attribution` settings being ignored entirely when one nested value was invalid; the rest of the block now still applies

1893 * Fixed repository, user and `--add-dir` skills, commands and skills-directory plugin manifests pre-approving their own tools via `allowed-tools` under managed `allowManagedPermissionRulesOnly`

1894 * Fixed safeguard block messages on Amazon Bedrock and Bedrock Mantle not showing a request ID; block messages now also show the message ID

1895 * Vertex AI: Fixed web search not being offered for models Claude Code doesn't recognize yet, such as newly released ones

1896 * Fixed Bash and PowerShell hiding a full disk quota behind "Exit code 1" and leaving large output files in temp

1897 * Fixed tool input validation errors naming only an unknown, missing or mistyped parameter when other parameters in the same call were also invalid; those are now listed too

1898 * Fixed pasted multi-line text being submitted line by line after the terminal's bracketed paste mode was reset mid-session

1899 * Fixed the prompt's example text flashing and disappearing at startup in projects with a `SessionStart` hook

1900 * Fixed a blank screen flashing before the first frame when starting in fullscreen mode

1901 * Fixed garbled, misplaced rows in the non-fullscreen renderer after the screen got shorter while still taller than the terminal, e.g. deleting a prompt line while a shell command streams output

1902 * Fixed a stale character left in the last column of a diff when a redrawn line's CJK character or emoji wrapped to the next row

1903 * Fixed the cursor landing before the end of a prompt recalled from history when the prompt contains a tab

1904 * Fixed the send-now hint showing ctrl+enter on terminals that send it as a newline (Windows Terminal before 1.25); it now shows ctrl+x ctrl+s there

1905 * Fixed `claude remote-control --debug` failing with "Unknown argument: --debug", although Remote Control's own eligibility error says to run with `--debug`

1906 * Fixed `/install-github-app` saying "cancelled" and then still pushing the branch and saving the API key secret; leaving now stops the remaining steps and reports what was already done

1907 * Fixed /feedback, /bug and /share on Bedrock, Vertex and other third-party providers still saving the report file after you cancelled during the save

1908 * Fixed plugin uninstall reporting success and deleting the plugin's saved options when its settings file still enabled it or could not be read; it now stops and names the file

1909 * Fixed plugin uninstall deleting a plugin's saved options and secrets when the list of installed plugins could not be read after the removal; they are now kept and the uninstall says so

1910 * Fixed a key typed right after `/` in `/skills` moving the skill list instead of reaching the search box

1911 * Fixed the terminal cursor jumping from the `/skills` search box to the skill list while typing, which could hide the caret and put IME input in the wrong place

1912 * Fixed lists with a scrollbar, such as `/skills` and `/mcp`, being two columns narrower outside fullscreen mode, where the scrollbar can never appear

1913 * Fixed the agent panel footer wrapping onto two lines with long rebound keys, and its "Esc to collapse" hint ignoring a rebound collapse key

1914 * Fixed a doubled `·` separator in the `/tasks` dialog footer when the stop-all-agents shortcut is unbound in `keybindings.json`

1915 * Fixed artifact publishes failing when Claude gave the version a label longer than 60 characters; the label is now shortened

1916 * Fixed screen-reader mode, quoted lists and very long lists dropping the blank lines at the top of a code block that opens a list item, directly or inside a quote

1917 * Fixed PDF page-read error messages: paths with accented or non-Latin characters now appear readably, and a folder named like "password" or "invalid" can no longer make the error name the wrong cause

1918 * Fixed vim mode `>>` indenting empty lines, `r` with a count longer than the line changing text, `2J` joining one line too many, and a count on the last line (`2dd`, `2>>`) shifting or deleting it

1919 * Fixed vim mode cursor placement: after `dd`, `dj`, `dG` or a whole-line `p`/`P` it lands on the first non-blank, `yy` no longer moves it, and Esc after an emoji no longer leaves it inside the emoji

1920 * Fixed vim mode ignoring a count typed before `.` when repeating `x`, `s`, `p`, `d` or `c`, and whole-line `p`/`P`, `o`, `O`, `J`, `>>` and `<<` acting on the wrong line when a line above wraps

1921 * Fixed vim mode leaving the cursor past the end of a prompt recalled from history or pulled back from the queue in normal mode, so `x` did nothing

1922 * \[VSCode] Fixed long replies falling behind the stream: the panel no longer re-parses the whole reply on every update

1923 * \[VSCode] Fixed the dictation mic button covering the message input's scrollbar when the input is tall enough to scroll

1924 * \[VSCode] Fixed Remote Control sessions started on this computer not opening from their Web entry in the session list; they now open the local conversation unless it's running elsewhere

1925 * \[VSCode] Fixed an editor tab's sign-in screen hanging silently after the extension host restarts; it now shows the "stopped responding" notice too

1926 * \[Cloud sessions] Fixed the next run time shown for an hourly routine being 30 minutes off for people in half-hour-offset time zones such as India

1927 * \[Claude Tag] Fixed auto-join channel patterns saved for one workspace in Claude Tag admin settings being ignored on an Enterprise Grid org-wide install; Claude now joins matching new channels

1928 * \[Claude Tag] Fixed Claude not responding in an Enterprise Grid channel shared between two workspaces of one organization when the channel's Claude Tag ve

1943

claude-apps-gateway Changed · +1 / -1 lines

from line 462

462462

463463### CI pipelines and remote machines

464464

465There is no service-token flow for unattended pipelines. Gateway sign-in always runs the browser device flow, so a CI job with no developer to approve the sign-in can't authenticate; configure those against your provider directly. Deploy `forceLoginMethod` and `forceLoginGatewayUrl` to developer machines and leave them off CI runners. On a machine whose managed settings set them, a session that authenticates with `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, or `apiKeyHelper` [exits at startup](/docs/en/errors#administrator-policy-requires-a-cloud-gateway-sign-in).

466466

467467Once a developer has signed in, each Claude Code session on that machine uses the gateway session, including non-interactive `claude -p` runs and sessions started by the Agent SDK. Claude Code applies the [gateway policy](/docs/en/claude-apps-gateway-config#managed) to each of them.

468468

claude-apps-gateway-config Changed · +4 / -0 lines

from line 306

306306

307307Set `forward_user_identity` only on an upstream whose `base_url` is a proxy you operate. The gateway sends developer emails to whatever server that `base_url` names. If the `base_url` is the Anthropic API, which is the default, the gateway refuses to start.

308308

309<Note>

310 If you set `forward_user_identity` on an Amazon Bedrock upstream, the gateway exits at startup with `Unrecognized key(s) in object: 'forward_user_identity'`. If your proxy sits in front of Bedrock, list it as a `provider: anthropic` upstream instead. The gateway sends that upstream the Anthropic Messages format, so your proxy has to [translate requests for Bedrock](/docs/en/llm-gateway-protocol#format-mismatch-with-the-upstream). To name each developer to AWS instead, see [Per-developer AWS cost attribution](#per-developer-aws-cost-attribution).

311</Note>

312

309313#### Amazon Bedrock

310314

311315For the client-side Amazon Bedrock deployment that the gateway replaces or fronts, see [Claude Code on Amazon Bedrock](/docs/en/amazon-bedrock). The gateway-side upstream:

claude-tag Changed · +1 / -1 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.

Nothing in the body moved in this read. What changed is above.

hooks Changed · +3 / -1 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 405

405405* **[Prompt hooks](#prompt-and-agent-hook-fields)** (`type: "prompt"`): send a prompt to a Claude model for single-turn evaluation. The model returns its decision as JSON. See [Prompt-based hooks](#prompt-based-hooks).

406406* **[Agent hooks](#prompt-and-agent-hook-fields)** (`type: "agent"`): spawn a subagent that can use tools like Read, Grep, and Glob to verify conditions before returning a decision. Agent hooks are experimental and may change. See [Agent-based hooks](#agent-based-hooks).

407407

408All matching hooks run in parallel. If you define the same handler in more than one settings file, it runs once. A plugin's or skill's copy of the same handler stays separate.

408When an event fires, its matching hooks run in parallel. If more than 12 of them are prompt or agent hooks, 12 of those run at once and the rest start as running ones finish. Each waiting hook's [`timeout`](#common-fields) starts counting when that hook starts.

409409

410If you define the same handler in more than one settings file, it runs once. A plugin's or skill's copy of the same handler stays separate.

411

410412Handlers run in the current directory with Claude Code's environment. If the current directory no longer exists, for example a worktree or temp directory that another shell deleted mid-session, Claude Code runs command hooks from the first of these that still exists: the directory the session started in, the project root, your home directory, or the system temp directory. Claude Code records a warning naming the fallback directory in the [debug log](#debug-hooks). For a worktree session that you start from the desktop app, see [What worktrees share with the main checkout](/docs/en/worktrees#what-worktrees-share-with-the-main-checkout).

411413

412414The `$CLAUDE_CODE_REMOTE` environment variable is `"true"` in remote web environments and not set in the local CLI. Claude Code v2.1.199 and later sets [`$CLAUDE_CODE_BRIDGE_SESSION_ID`](/docs/en/env-vars) to the [Remote Control](/docs/en/remote-control) session ID while the local session has an active Remote Control connection.

from line 4015

40134015

40144016Set `type` to `"agent"` and provide a `prompt` string, using `$ARGUMENTS` as a placeholder for the hook input JSON. The configuration fields are the same as [prompt hooks](#prompt-hook-configuration), except that agent hooks have a longer default timeout of 60 seconds and no `continueOnBlock` field.

40154017

4016The response schema is `{ "ok": true }` to allow or `{ "ok": false, "reason": "..." }` to block. On `ok: false`, Claude Code handles an agent hook the way it handles a [prompt hook with `continueOnBlock: true`](#response-schema) on the same event; agent hooks have no `continueOnBlo

4018The response schema is `{ "ok": true }` to allow or `{

hooks-guide Changed · +1 / -1 lines

from line 473

473473

474474## How hooks work

475475

476Claude Code fires hook events at specific points in its lifecycle. When an event fires, Claude Code runs all matching hooks in parallel; see [Hook handler fields](/docs/en/hooks#hook-handler-fields) for how duplicate handlers are treated. The table below shows each event and when it triggers:

476Claude Code fires hook events at specific points in its lifecycle. When an event fires, Claude Code runs the matching hooks in parallel; see [Hook handler fields](/docs/en/hooks#hook-handler-fields) for how duplicate handlers are treated. The table below shows each event and when it triggers:

477477

478478| Event | When it fires |

479479| :- | :- |

plugins/mods/interface Changed · +1 / -1 lines

from line 344

344344

345345### Draw in the VS Code extension

346346

347In the VS Code extension, what a mod draws appears in the chat panel with extension version 2.1.299 or later, in a session that [fetches feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching). In a `ui.render` hook for the panel, `e.surface` is `vscode`. To check which sites and elements the panel draws, and which props it ignores, see the [render sites](/docs/en/plugins/mods/reference#render-sites) and [elements](/docs/en/plugins/mods/reference#elements) tables.

347In the VS Code extension, what a mod draws appears in the chat panel with extension version 2.1.299 or later. A session that [doesn't fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), such as one on Amazon Bedrock, needs 2.1.304 or later. In a `ui.render` hook for the panel, `e.surface` is `vscode`. To check which sites and elements the panel draws, and which props it ignores, see the [render sites](/docs/en/plugins/mods/reference#render-sites) and [elements](/docs/en/plugins/mods/reference#elements) tables.

348348

349349To make a mod work in the panel as well as the terminal, account for these differences:

350350

plugins/mods/overview Changed · +1 / -1 lines

from line 191

191191| `claude` in a terminal, including an editor's integrated terminal and the JetBrains plugin | Yes | Yes |

192192| The Code tab of the Desktop app, except in a WSL session | Yes | Yes, except elements the [elements table](/docs/en/plugins/mods/reference#elements) marks terminal-only |

193193| A [WSL session](/docs/en/desktop-wsl) in the Desktop app | No, because plugins aren't available in WSL sessions | No |

194| The VS Code extension's chat panel | Yes | Yes, with extension version 2.1.299 or later, in a session that [fetches feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching). The [render sites](/docs/en/plugins/mods/reference#render-sites) and [elements](/docs/en/plugins/mods/reference#elements) tables mark what the panel draws. |

194| The VS Code extension's chat panel | Yes | Yes, with extension version 2.1.299 or later. A session that [doesn't fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), such as one on Amazon Bedrock, needs 2.1.304 or later. The [render sites](/docs/en/plugins/mods/reference#render-sites) and [elements](/docs/en/plugins/mods/reference#elements) tables mark what the panel draws. |

195195| `claude -p` and the [Agent SDK](/docs/en/agent-sdk/overview) | Yes | No |

196196| [Remote Control](/docs/en/remote-control) from claude.ai or the mobile app | Yes, in the session on your machine | In the terminal on your machine |

197197| A [cloud session](/docs/en/claude-code-on-the-web) | Yes, for a plugin that [reaches the cloud session](/docs/en/cloud-environments#what-carries-over-from-your-setup) | No |

plugins/mods/reference Changed · +1 / -1 lines

from line 221

221221

222222A render site is an extension point in Claude Code's interface. Each row is a value of `e.component` in a `ui.render` hook, with the fields of `e.props` and the apps that render it. `e.surface` names the app that's drawing, such as `terminal`, `desktop`, or `vscode`. [Change what Claude Code already draws](/docs/en/plugins/mods/interface#change-what-claude-code-already-draws) shows what a hook can do at a site, with an example of each choice.

223223

224Rendering in the VS Code extension requires extension version 2.1.299 or later and a session that [fetches feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching). [Draw in the VS Code extension](/docs/en/plugins/mods/interface#draw-in-the-vs-code-extension) lists what the extension draws differently.

224Rendering in the VS Code extension requires extension version 2.1.299 or later. A session that [doesn't fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching) needs 2.1.304 or later. [Draw in the VS Code extension](/docs/en/plugins/mods/interface#draw-in-the-vs-code-extension) lists what the extension draws differently.

225225

227227| :- | :- | :- | :- |

plugins/mods/troubleshoot Changed · +1 / -1 lines

from line 245

245245

246246* **The site or element isn't drawn in that app**: look up your site in the [render sites](/docs/en/plugins/mods/reference#render-sites) table and your elements in the [elements](/docs/en/plugins/mods/reference#elements) table. For an element the app lacks, check `e.surface` in the hook and return a tree the app can draw.

247247* **The VS Code extension is older than 2.1.299**: the chat panel draws for mods from [extension version](/docs/en/vs-code#install-the-extension) 2.1.299. Check the version in VS Code's Extensions view and update the extension there.

248* **The VS Code session doesn't fetch feature flags**: drawing in the chat panel requires it. Sessions on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, or through a [Claude apps gateway](/docs/en/claude-apps-gateway), skip it, among others that [Features that need feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) lists. To see the drawing in such a session, run `claude` in a terminal instead, such as VS Code's integrated terminal.

248* **The extension is older than 2.1.304 and the session doesn't fetch feature flags**: update the extension, or run `claude` in VS Code's integrated terminal instead. Sessions on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry skip the fetch. For the others that skip it, such as a [Claude apps gateway](/docs/en/claude-apps-gateway) session, see [Features that need feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching).

249249

250250## An edit or a value is lost

251251

vs-code Changed · +1 / -1 lines

from line 497

497497

498498### Plugins that draw in the panel

499499

500A plugin that contains a [mod](/docs/en/plugins/mods/overview) can draw in the chat panel. Drawing requires extension version 2.1.299 or later and a session that [fetches feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching). From such a plugin you can see:

500A plugin that contains a [mod](/docs/en/plugins/mods/overview) can draw in the chat panel. Drawing requires extension version 2.1.299 or later. A session that [doesn't fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), such as one on Amazon Bedrock, needs 2.1.304 or later. From such a plugin you can see:

501501

502502* A pane beside the conversation or above the prompt box

503503* A toast or a status line above the prompt box