One read of Claude Code CLIclaude-code-20260930T043702Z
13 pages moved out of 210 read.
Pages moved
13
significant first
Pages read
210
in this capture
Captured
04:37 UTC
Corpus hash
2b92c9d8138b
corpus-hash
What this read moved
1-13 of 13claude-apps-gateway-config Changed · +3 / -3 lines
from line 760
760760
761761The gateway's [telemetry](#telemetry) configuration pushes `OTEL_EXPORTER_OTLP_ENDPOINT`, so setting `telemetry.forward_to` triggers the dialog on each interactive client. The dialog protects the developer's machine from a compromised or hostile gateway, not the organization from the developer.
762762
763A non-interactive run with the `-p` flag can't show the dialog. It applies the pushed settings for that run only and doesn't record them as approved, so the developer's next interactive session still shows the dialog. Before v2.1.207, a non-interactive run saved the settings as approved and no later interactive session showed the dialog for them.
763A [non-interactive run](/docs/en/server-managed-settings#security-approval-dialogs), such as `claude -p` or an Agent SDK session, can't show the dialog. It applies the pushed settings for that run only and doesn't record them as approved, so the developer's next interactive session still shows the dialog. Before v2.1.207, a non-interactive run saved the settings as approved and no later interactive session showed the dialog for them.
764764
765If a developer declines, Claude Code exits that session rather than applying the policy. When you push a new hook, or any env var that triggers the dialog, to a broad policy, Claude Code therefore shows the dialog to every matching developer. It shows the dialog in a running session on the next hourly poll, and otherwise at the developer's next startup.
765If a developer declines, Claude Code exits that session rather than applying the policy. When you push a new hook, or any env var that triggers the dialog, to a broad policy, every matching developer therefore sees the dialog in their interactive sessions. A running interactive session shows it on the next hourly poll, and otherwise it appears at the developer's next interactive startup.
766766
767767The `cli` key was named `settings` in earlier releases. That spelling is still accepted as an alias, but new deployments should use `cli`.
768768
errors Changed · +19 / -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 214
214214| `Ultrareview clones <owner>/<repo> in the cloud with the GitHub account connected to your Claude account, and none is connected` | [Command-line errors](#no-github-account-is-connected-to-your-claude-account) |
215215| `Your connected GitHub account can't see <owner>/<repo>` | [Command-line errors](#your-connected-github-account-cant-see-the-repository) |
216216| `The GitHub App preflight failed transiently (network or service hiccup) — retry in a moment to start from GitHub instead` | [Command-line errors](#the-github-app-preflight-failed-transiently) |
217| `Not uploading this working tree` with `the upload cannot follow that setting` | [Command-line errors](#the-repository-upload-cant-follow-a-git-setting) |
217218| `GitHub isn't connected to your Claude account, so this repository can't be cloned in the cloud` | [Command-line errors](#github-isnt-connected-to-your-claude-account) |
218219| `Single sign-on authorization needed` | [Command-line errors](#single-sign-on-authorization-needed) |
219220| `Failed to resume the conversation` | [Command-line errors](#failed-to-resume-the-conversation) |
from line 2846
28452846Claude Code turns `claude import` on through a feature flag it fetches from Anthropic and caches on disk. This message means the cached value is off. The cause is usually one of the following:
28462847
28472848* You haven't started a session since installing, so Claude Code hasn't fetched the flag yet. The first `claude import` can print this even when the feature is available to you.
2848* You use Claude Code through Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or Claude Platform on AWS, or through a [Claude apps gateway](/docs/en
2849* You use
mcp Changed · +3 / -3 lines
from line 480
480480 * In [cloud sessions](/docs/en/claude-code-on-the-web), an MCP call to a plugin server that isn't connected yet, such as right after an idle session wakes, starts the server on demand and waits for it to connect
481481* **Path placeholders**: `${CLAUDE_PLUGIN_ROOT}` resolves to the plugin's installation directory, `${CLAUDE_PLUGIN_DATA}` to its [persistent state](/docs/en/plugins/components#path-variables-and-persistent-data) directory, and `${CLAUDE_PROJECT_DIR}` to the stable project root. Substitution applies to:
482482 * `stdio` servers: `command`, `args`, `env`
483 * `http`, `sse`, and `ws` servers: `url`, `headers`, and `headersHelper`. Before v2.1.195, `headersHelper` passed the placeholder through as a literal string
483 * `http`, `sse`, and `ws` servers: `url`, `headers`, and `headersHelper`
484484* **User environment access**: access to the same environment variables as manually configured servers
485485* **Multiple transport types**: support for stdio, SSE, HTTP, and WebSocket transports, though transport support may vary by server
486486
from line 993
993993
994994| Where you configured the server | Working directory |
995995| :- | :- |
996| A [plugin](/docs/en/plugins/components#mcp-servers) | The plugin's root directory. Requires Claude Code v2.1.195 or later |
996| A [plugin](/docs/en/plugins/components#mcp-servers) | The plugin's root directory |
997997| A project `.mcp.json` or a [local-scope](#local-scope) server | The project directory the server is declared in |
998998| An agent file in your project, a server from the SDK's `mcpServers` option or `setMcpServers()` method, or [`--mcp-config`](/docs/en/cli-reference) | The session's [primary working directory](/docs/en/permissions#working-directories) |
999999| [User scope](#user-scope), [managed MCP](/docs/en/managed-mcp), a [claude.ai connector](#use-mcp-servers-from-claude-ai), or an agent file from outside your project, including one from an `--add-dir` directory | Your configuration directory, `~/.claude` unless you set [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars) |
from line 1306
13061306
13071307Your server receives whichever arguments Claude chose, so keep validating the combination server-side.
13081308
1309When Claude Code can't produce a schema the API accepts, or on a deployment that doesn't receive the remote configuration that enables the rewrite, it skips that one tool, records the reason in the server's log, and leaves the server's other tools available. Versions earlier than v2.1.195 skip every tool whose input schema has a root-level `anyOf`, `oneOf`, or `allOf`.
1309When Claude Code can't produce a schema the API accepts, or on a deployment that doesn't receive the remote configuration that enables the rewrite, it skips that one tool, records the reason in the server's log, and leaves the server's other tools available.
13101310
13111311## Tools with invalid input schemas
13121312
model-config Changed · +4 / -4 lines
from line 273
273273
274274| Delivery mechanism | CLI and IDE | Desktop local sessions | Web, mobile, and cloud sessions | Agent SDK and non-interactive | Cowork |
275275| :- | :- | :- | :- | :- | :- |
276| [Server-managed settings](/docs/en/server-managed-settings) from the admin console | Enforced | Enforced | Enforced, except in [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions | Enforced | Not delivered |
276| [Server-managed settings](/docs/en/server-managed-settings) from the admin console | Enforced | Enforced | Enforced, except in [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions | Enforced | Remote Cowork sessions: the server checks the model. On the user's machine: not delivered. |
277277| [MDM or managed settings files](/docs/en/managed-settings#delivery-mechanisms) | Enforced | Enforced | Not delivered in Anthropic-hosted environments; in [self-hosted environments](/docs/en/self-hosted-environments), enforced from the runner image per [how Claude Code combines managed sources](/docs/en/managed-settings#how-claude-code-combines-managed-sources) | Enforced | Enforced where deployed |
278278
279279* [Cloud sessions](/docs/en/claude-code-on-the-web), including those you start from the Desktop app, run on Anthropic-managed VMs by default: settings deployed to your device do not reach them, so deliver the allowlist through server-managed settings. Sessions your organization routes to a [self-hosted environment](/docs/en/self-hosted-environments) run on your own compute and also read the managed settings file in the runner image. [How Claude Code combines managed sources](/docs/en/managed-settings#how-claude-code-combines-managed-sources) says when that file applies. A mid-session model switch in a cloud session is rejected when the requested model is excluded by the allowlist. When the `availableModels` list in your server-managed settings is non-empty, the server rejects a request to start a cloud session at claude.ai/code or from the Desktop app on a model the list excludes.
280280* [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions run in cloud environments but don't receive server-managed settings; in a [self-hosted environment](/docs/en/self-hosted-environments), they still read the managed settings file in the runner image. To set the model for those sessions, see [Choose the model for a scope](https://claude.com/docs/claude-tag/admins/customize#choose-the-model-for-a-scope) in the Claude Tag admin guide.
281* Cowork, the agentic-work tab in the Claude Desktop app, runs its sessions on Claude Code but, by design, does not receive server-managed settings from the claude.ai admin console. A managed settings file applies to Cowork sessions when it is present where the session runs; remote Cowork sessions run on Anthropic-managed VMs, where a device-deployed file is not present.
281* Cowork, the agentic-work tab in the Claude Desktop app, runs its sessions on Claude Code but, by design, does not receive server-managed settings from the claude.ai admin console. When the `availableModels` list in your server-managed settings is non-empty and a user picks a model outside it, the server rejects that model for a remote Cowork session. A managed settings file applies to Cowork sessions when it is present where the session runs; remote Cowork sessions run on Anthropic-managed VMs, where a device-deployed file is not present.
282282* Sessions on [third-party providers](/docs/en/server-managed-settings#platform-availability) such as Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and [Claude Platform on AWS](/docs/en/claude-platform-on-aws) do not receive server-managed settings, so deliver the allowlist through MDM or managed settings files there.
283283* Server-managed delivery also requires the session to authenticate with an [eligible login or key](/docs/en/server-managed-settings#platform-availability). Fleets that generate keys only through an [`apiKeyHelper`](/docs/en/settings-reference#apikeyhelper) script should deliver the allowlist through MDM or managed settings files.
284284* The Desktop Code tab also hosts [SSH sessions](/docs/en/desktop#ssh-sessions), which read the managed settings file from the remote host they run on. See [Desktop managed settings](/docs/en/desktop#managed-settings).
from line 958
958958| - | - |
959959| `DISABLE_PROMPT_CACHING` | Set to `1` to disable prompt caching for all models. Takes precedence over the per-model settings |
960960| `DISABLE_PROMPT_CACHING_HAIKU` | Set to `1` to disable prompt caching for the [default Haiku model](/docs/en/prompt-caching#disable-prompt-caching) |
961| `DISABLE_PROMPT_CACHING_SONNET` | Set to `1` to disable prompt caching for Sonnet models only |
962| `DISABLE_PROMPT_CACHING_OPUS` | Set to `1` to disable prompt caching for Opus models only |
961| `DISABLE_PROMPT_CACHING_SONNET` | Set to `1` to disable prompt caching for the [default Sonnet model](/docs/en/prompt-caching#disable-prompt-caching) |
962| `DISABLE_PROMPT_CACHING_OPUS` | Set to `1` to disable prompt caching for the [default Opus model](/docs/en/prompt-caching#disable-prompt-caching) |
963963| `DISABLE_PROMPT_CACHING_FABLE` | Set to `1` to disable prompt caching for Fable models only |
964964
965965To choose the cache TTL for the main conversation and for subagents separately, see [choose the TTL yourself](/docs/en/prompt-caching#choose-the-ttl-yourself). For what triggers a cache miss, see [How Claude Code uses prompt caching](/docs/en/prompt-caching).
permission-modes Changed · +2 / -6 lines
from line 346
346346* `git commit --amend` when the commit at HEAD was not created in this session
347347* From v2.1.198, `git commit --amend` when the commit at HEAD has already been pushed. A message-only reword is not blocked: `--amend -m` with nothing newly staged, on a commit that Claude created during this session
348348* `terraform destroy`, `pulumi destroy`, `cdk destroy`, or `terragrunt destroy`, and applying a plan that destroys resources
349
350Claude Code v2.1.195 and later block more categories by default. Several depend on [environment](/docs/en/auto-mode-config#define-trusted-infrastructure) entries, such as sensitive remote targets and protected IaC scopes, that you can narrow to concrete names.
351
352349* Writing to a secret manager, or changing DNS records or TLS certificates
353350* Merging a pull request no human has approved, approving Claude's own pull request, or disabling CI checks
354351* Posting a comment that is itself a command to automation, such as `atlantis apply` or a bot's `/deploy` or `/merge`
from line 362
365362* Launching an autonomous agent loop that runs without human approval or a sandbox, such as one started with `--dangerously-skip-permissions` or `--no-sandbox`. As of v2.1.198 this also covers running a third-party agent or eval harness with isolation and per-action approval disabled, such as a runner started with `--yes-always`
366363* [Claude in Chrome](/docs/en/chrome) browser actions that could send page content, cookies, or credentials off-origin
367364
365Several of these categories depend on [environment](/docs/en/auto-mode-config#define-trusted-infrastructure) entries, such as sensitive remote targets and protected IaC scopes, that you can narrow to concrete names.
366
368367Claude Code v2.1.198 and later also block these by default:
369368
370369* Deleting files in `/tmp`, `$TMPDIR`, or another shared scratch or cache directory by wildcard, glob, or age filter rather than by a specific named path
from line 410
411410* Reading `.env` and sending credentials to their matching API
412411* Read-only HTTP requests
413412* Pushing to any branch of the repository you're working in, including the default branch. A non-default branch whose name marks it as a deploy or publication target, such as `production` or `gh-pages`, isn't covered: the classifier judges a push there on its own terms. The push's content is still checked against the other rules, [`permissions.deny` rules](/docs/en/permissions#manage-permissions) can still block push commands [as written](/docs/en/permissions#bash-rule-limits) in every mode, and the remote's own branch protection still applies. Before v2.1.211, only pushes to the branch you started on, branches Claude created, and routine pushes to the default branch were allowed by default, and before v2.1.203 any direct push to the default branch was blocked
414
415Claude Code v2.1.195 and later also allow these by default:
416
417413* Deleting the exact jobs Claude created earlier in the same session
418414* Reading, reviewing, or writing security-related code, configs, and threat models as part of your task
419415* Messages between agents working together in the same multi-agent session
prompt-caching Changed · +4 / -2 lines
from line 342
342342| - | - |
343343| `DISABLE_PROMPT_CACHING` | Disable for all models |
344344| `DISABLE_PROMPT_CACHING_HAIKU` | Disable for the default Haiku model |
345| `DISABLE_PROMPT_CACHING_SONNET` | Disable for Sonnet only |
346| `DISABLE_PROMPT_CACHING_OPUS` | Disable for Opus only |
345| `DISABLE_PROMPT_CACHING_SONNET` | Disable for the default Sonnet model |
346| `DISABLE_PROMPT_CACHING_OPUS` | Disable for the default Opus model |
347347| `DISABLE_PROMPT_CACHING_FABLE` | Disable for Fable only |
348348
349349`DISABLE_PROMPT_CACHING_HAIKU` applies to the default Haiku model, the model the `haiku` alias resolves to. It disables caching wherever that model runs, including the main conversation when it is your main model. Covering the main conversation requires Claude Code v2.1.283 or later.
from line 351
351351The variable also covers a background model you set with the deprecated `ANTHROPIC_SMALL_FAST_MODEL` variable, when that model differs from your main model.
352352
353353A different Haiku version that you pin as your main model keeps caching; set `DISABLE_PROMPT_CACHING` to disable caching for it.
354
355`DISABLE_PROMPT_CACHING_SONNET` and `DISABLE_PROMPT_CACHING_OPUS` each apply to the model the `sonnet` or `opus` alias resolves to. If you set any other Sonnet or Opus model ID as your main model, that model keeps caching. For example, a session on `claude-sonnet-5` keeps caching while `sonnet` resolves to `claude-sonnet-5-5`. To disable caching for that model, set `DISABLE_PROMPT_CACHING`.
354356
355357To set caching policy across an organization, put any of these or the [TTL variables](#cache-lifetime) in the `env` block of [managed settings](/docs/en/managed-settings). For normal use, leave caching enabled.
356358
claude-code-on-the-web Changed · +1 / -0 lines
from line 134
134134* The directory must be a git repository with at least one commit
135135* The bundled repository must be under 100 MB. Larger repositories fall back to bundling only the current branch, then to a single squashed snapshot of the working tree, and fail if the snapshot is still too large
136136* Untracked files are not included; run `git add` on files you want the cloud session to see
137* On macOS, Linux, and WSL, Claude Code refuses the upload when it can't follow a git setting that affects which attribute rules apply to your files, such as `core.attributesFile` set in an included config file. The [refusal message](/docs/en/errors#the-repository-upload-cant-follow-a-git-setting) names the setting and the fix
137138* Sessions created from a bundle can push back to a GitHub remote only when your [GitHub connection](#github-authentication-options) has push access to that repository
138139
139140### Send follow-ups from the CLI
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.
fullscreen Changed · +1 / -1 lines
from line 264
264264
265265With mouse capture disabled, keyboard scrolling with `PgUp`, `PgDn`, `Ctrl+Home`, and `Ctrl+End` still works, and your terminal handles selection natively. You lose click-to-position-cursor, click-to-expand, URL clicking, and wheel scrolling inside Claude Code.
266266
267To keep wheel scrolling but turn off click, drag, and hover handling, set `CLAUDE_CODE_DISABLE_MOUSE_CLICKS=1` instead. Requires Claude Code v2.1.195 or later. `CLAUDE_CODE_DISABLE_MOUSE` takes precedence when both variables are set.
267To keep wheel scrolling but turn off click, drag, and hover handling, set `CLAUDE_CODE_DISABLE_MOUSE_CLICKS=1` instead. `CLAUDE_CODE_DISABLE_MOUSE` takes precedence when both variables are set.
268268
269269With clicks disabled, Claude Code still captures the mouse, so the wheel and touchpad scroll the conversation but left clicks do nothing inside Claude Code. You still need to hold your terminal's key for native click-and-drag selection. Right-click and middle-click paste continue to work on terminals that support them.
270270
hooks Changed · +0 / -4 lines
from line 290
290290
291291A matcher on the regular-expression path is tested with JavaScript's `RegExp.prototype.test`, which succeeds on a match anywhere in the value. `Edit.*` matches both `Edit` and `NotebookEdit`; wrap the pattern in `^` and `$`, as in `^Edit$`, when you need a whole-string match.
292292
293Hyphens in the exact-match set require Claude Code v2.1.195 or later. On earlier versions a hyphenated name like `code-reviewer` is evaluated as an unanchored regular expression, so it also fires for `senior-code-reviewer`; anchor it as `^code-reviewer$` on those versions to match only that name.
294
295293`FileChanged` and `StopFailure` use a narrower exact-match set of letters, digits, `_`, and `|` only. A hyphen, space, or comma in a matcher for those two events keeps it on the regular-expression path, and only `|` separates alternatives. Every other event with matcher support in the table that follows accepts `|` or `,`.
296294
297295The `FileChanged` event doesn't follow these rules when building its watch list. See [FileChanged](#filechanged).
from line 361
363361* `mcp__memory__.*` matches all tools from the `memory` server
364362* `mcp__brave-search__.*` matches all tools from a server whose name contains a hyphen
365363* `mcp__.*__write.*` matches any tool whose name starts with `write` from any server
366
367Hyphens in the exact-match set require Claude Code v2.1.195 or later. On earlier versions a bare hyphenated prefix like `mcp__brave-search` is evaluated as an unanchored regular expression and matches every tool from that server. The `mcp__brave-search__.*` form works on every version.
368364
369365Tools from a [plugin-bundled MCP server](/docs/en/mcp#plugin-provided-mcp-servers) use a scoped server segment that includes the plugin name: `mcp__plugin_<plugin-name>_<server-name>__<tool>`. A matcher written against the bare server key never fires for these tools. For a plugin named `my-plugin` that bundles a server under the key `db`, a `query` tool appears as `mcp__plugin_my-plugin_db__query`, so the matcher for every tool from that server is `mcp__plugin_my-plugin_db__.*`. Use the same scoped tool name in a handler's [`if` field](#common-fields). See [Plugin-provided MCP servers](/docs/en/mcp#plugin-provided-mcp-servers) for how the scoped name is built.
370366
server-managed-settings Changed · +1 / -1 lines
from line 276
276276* **An interactive session that can't show the dialog**: Claude Code doesn't apply the delivered settings and keeps the last-approved settings. The dialog appears in the next session that can show it. Requires Claude Code v2.1.211 or later.
277277* **`claude install` or `claude update`**: Claude Code doesn't show the dialog during either command. The command runs with the last-approved settings, and the dialog appears in your next interactive session. If Claude Code waits for the settings fetch at startup, such as with [`forceRemoteSettingsRefresh`](#enforce-fail-closed-startup) set or on a [Claude apps gateway](/docs/en/claude-apps-gateway) deployment, it shows the dialog during the command instead, and an install run from a pipe fails; see [`Raw mode is not supported` during install](/docs/en/troubleshoot-install#raw-mode-is-not-supported-during-install). Before v2.1.246, Claude Code tried to show the dialog during these commands too.
278278* **An error closes the dialog before you answer**: Claude Code doesn't apply the delivered settings and keeps the last-approved settings. It shows the dialog again in the next session that can show it.
279* **A non-interactive run**, such as `claude -p` or an Agent SDK session: Claude Code can't show the dialog, so when the delivered settings would require approval, it applies them for that run only. It doesn't record them as approved or write them to the [local cache](#fetch-and-caching-behavior), and the next interactive session shows the dialog. Until a user approves in an interactive session, each non-interactive run fetches the settings again at startup. Before v2.1.207, a non-interactive run saved the settings as approved, so later interactive sessions never showed the dialog for them.
279* **A non-interactive run**, such as `claude -p`, an Agent SDK session, or a session in the VS Code extension's chat panel or the desktop app's Code tab: Claude Code can't show the dialog, so when the delivered settings would require approval, it applies them for that run only. It doesn't record them as approved or write them to the [local cache](#fetch-and-caching-behavior), and the next interactive session shows the dialog. Until a user approves in an interactive session, each non-interactive run fetches the settings again at startup. Before v2.1.207, a non-interactive run saved the settings as approved, so later interactive sessions never showed the dialog for them.
280280
281281#### Environment variables and the approval dialog
282282
sub-agents Changed · +0 / -2 lines
from line 802
802802}
803803```
804804
805A hyphenated matcher like `db-agent` matches exactly on Claude Code v2.1.195 or later. On earlier versions it is evaluated as an unanchored regular expression and also fires for any agent type that contains it, such as `prod-db-agent`; anchor it as `^db-agent$` on those versions.
806
807805See [Hooks](/docs/en/hooks) for the complete hook configuration format.
808806
809807## Work with subagents
tools-reference Changed · +0 / -4 lines
from line 344
344344
345345### WebSocket source
346346
347<Note>
348 The WebSocket source requires Claude Code v2.1.195 or later.
349</Note>
350
351347When a server already pushes events over a WebSocket, Claude can connect to it directly instead of writing a polling script. Each kind of socket activity either becomes an event or ends the watch:
352348
353349* **Text messages**: each one becomes one event, even when the message spans multiple lines.