One read of Claude Code CLIclaude-code-20261002T030701Z
10 pages moved out of 220 read.
Pages moved
10
significant first
Pages read
220
in this capture
Captured
03:07 UTC
Corpus hash
1b8504134558
corpus-hash
What this read moved
1-10 of 10artifacts Changed · +9 / -0 lines
from line 98
9898
9999Claude reads a page someone else wrote the way it reads a web page with [WebFetch](/docs/en/tools-reference#webfetch-tool-behavior): it gets a summary of what it asked about rather than the raw page, and the summary reports instructions written into the page instead of relaying them. Claude Code also saves the page's full source to a local file, which Claude can open when it needs the exact content, such as to republish the artifact as an [editor](#let-someone-edit-with-you).
100100
101Claude Code asks for your approval before Claude reads the artifact in these cases, in addition to any prompt your permission mode or rules call for:
102
103* **Cloud session without network access**: for a [cloud environment](/docs/en/cloud-environments#access-levels), that's the **None** level. In [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), the classifier can approve instead; in a [Cowork](https://claude.com/product/cowork) session, the approval is yours alone.
104* **Another organization's public artifact**: Claude Code asks you first, even in auto mode. Where Claude Code can't ask you, such as in `bypassPermissions` mode, Claude can't read the artifact. Claude can read these artifacts only while [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) is on.
105* **Unconfirmed owner or network setting**: when Claude Code can't confirm who made the artifact, or can't confirm a cloud session's network setting, it asks, and your approval covers that one request.
106* **Plan mode, or feature-flag fetching turned off**: in [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), or if you turned [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) off, Claude Code asks before the Artifact tool reads an artifact someone else in your organization made.
107
108When Claude reads the artifact with WebFetch, WebFetch's own [prompting rules](/docs/en/tools-reference#webfetch-tool-behavior) still apply.
109
101110## Collect comments on an artifact
102111
103112When you share an artifact within your organization, the people you share it with can leave comments on the page, and you can have Claude read those comments and reply to them. You need Claude Code v2.1.221 or later. Claude reads the comments in two cases:
model-config Changed · +13 / -1 lines
#### Effort level after a fallback
from line 520
520520
521521The fallback model is checked against [`availableModels`](#restrict-model-selection). When it is blocked, no fallback occurs. The refusal is shown as a normal error and the session's model is unchanged.
522522
523#### Effort level after a fallback
524
525When Claude Code switches your session to the fallback model, it keeps the effort level the flagged request ran at in place of that model's default effort. For example, a session on Opus 5.5 at its default `medium` that falls back to Opus 4.8 stays at `medium`, although Opus 4.8 defaults to `high`.
526
527A different level applies in cases such as these:
528
529* **Settings or organization default**: a level in your settings that applies to the fallback model, or a default effort your organization set for it, applies instead.
530* **Your own change**: once you choose an effort level, pick a model in `/model`, or resume the session later, the flagged request's level no longer carries over.
531* **Skill effort**: a level that a skill's `effort` frontmatter set for the flagged request applies to that turn, and later turns run at the level the [effort resolution order](#adjust-effort-level) gives the fallback model.
532
533The session header shows the level in effect next to the model name. To change it, run `/effort` in the session.
534
523535#### Check what triggered fallback
524536
525537Fallback can trigger on the first request of a session, before you send anything unusual, because the first request carries workspace context such as your CLAUDE.md content and git status. A repository that contains security or biology material can trip the classifier on that context alone.
from line 588
576588
5775891. 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))
5785902. 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)
5793. The model's default effort: `high` on every model that supports effort, except that Opus 5.5 and Sonnet 5.5 default to `medium`, 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
5913. The model's default effort: `high` on every model that supports effort, except that Opus 5.5 and Sonnet 5.5 default to `medium`, 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. After an automatic model fallback, see [Effort level after a fallback](#effort-level-after-a-fallback) for the level that applies.
580592
581593Opus 5.5 starts at `medium` unless one of the sources above sets a level for it, and a top-level `effortLevel` in your user settings file doesn't count for Opus 5.5. That key is the older form `/effort` wrote before Claude Code saved levels per model: it keeps applying where it applied before, on Opus 5, Fable 5.1, and earlier models, while Opus 5.5 and models released after it start at their own default until you choose a level for them with `/effort` or the `/model` picker. A top-level `effortLevel` in project, local, or managed settings, or one passed with `--settings`, applies to every model.
582594
plugins/manifest-reference Changed · +22 / -1 lines
from line 255
255255
256256`hooks` takes a `.json` file path, an inline hooks object in the same shape as [`hooks` in `settings.json`](/docs/en/hooks#configuration), or an array mixing both. For hook events and handler fields, see the [hooks reference](/docs/en/hooks#hook-events).
257257
258Claude Code merges whatever you declare with `hooks/hooks.json` when that file exists.
258A hooks file wraps the event map in a top-level `"hooks"` key, the shape [`hooks/hooks.json`](/docs/en/plugins/components#hooks) uses. A file that contains only the event map, without that wrapper, fails to load. An inline object is the event map itself, with no wrapper.
259259
260Claude Code merges whatever you declare with `hooks/hooks.json` when that file exists. This array loads one hooks file and declares one inline `PostToolUse` hook:
261
260262```json theme={null}
261263{
262264 "hooks": [
from line 277
275277}
276278```
277279
280The file that array names carries the `"hooks"` wrapper around its own event map:
281
282```json config/extra-hooks.json theme={null}
283{
284 "hooks": {
285 "PreToolUse": [
286 {
287 "matcher": "Bash",
288 "hooks": [
289 { "type": "command", "command": "\"${CLAUDE_PLUGIN_ROOT}\"/scripts/check-command.sh" }
290 ]
291 }
292 ]
293 }
294}
295```
296
278297### `mcpServers`
279298
280299`mcpServers` takes a `.json` file path, an MCP bundle path or URL, an inline map, or an array mixing them. For server config fields, see [plugin-provided MCP servers](/docs/en/mcp#plugin-provided-mcp-servers).
from line 389
370389
371390* **`skills`**: also accepts `"."`. Both `"."` and `"./"` denote the plugin root. Before v2.1.221, `"."` failed manifest validation, so use `"./"` when the plugin must load on earlier versions
372391* **`mcpServers`**: also accepts an `https://` bundle URL
392
393`experimental.evals` isn't a component path, so the rules in this section don't cover it, and `claude plugin eval` checks the value when it runs instead. It names a directory below the plugin root, such as `"quality/evals"`, with or without the `./` prefix. With an array, only the first entry is used. For what the value accepts and what happens with an unusable one, see [Use a different eval directory](/docs/en/plugin-evals#use-a-different-eval-directory).
373394
374395### Containment and existence
375396
routines Changed · +1 / -5 lines
from line 325
325325
326326Each repository you add is cloned on every run. Claude starts from the repository's default branch unless your prompt specifies otherwise.
327327
328Claude pushes its work to branches prefixed with `claude/`, which are always accepted. When your prompt directs Claude to push to another branch, Claude Code checks the push first and rejects it if any of the following is true:
329
330* The branch is protected on GitHub
331* Someone else has an open pull request from that branch
332* The branch carries commits authored by someone other than you
328Claude pushes its work to a branch prefixed with `claude/` unless your prompt directs it to push to another branch. To control which branches a run can push to, use branch protection rules or rulesets on GitHub. For runs on Anthropic-managed infrastructure, and for self-hosted runs that push through [Anthropic's git proxy](/docs/en/self-hosted-environments-deploy#use-the-anthropic-git-proxy), GitHub applies them to the GitHub access you connected, so a rule that access can bypass doesn't block a run's push. A self-hosted run that pushes with the git credentials your deployment provides is checked against those instead. See [Configure git](/docs/en/self-hosted-environments-deploy#configure-git).
333329
334330### Connectors
335331
vs-code Changed · +17 / -3 lines
### Continue conversations after a reload ### Move a running command or subagent to the background
from line 203
203203* **Session titles**: new sessions receive AI-generated titles based on your first message.
204204* **Rename and archive**: hover over a session to reveal these actions. Rename to give it a descriptive title, or archive to move it to the **Archived sessions** group at the bottom of the list.
205205
206If the conversation is open in another Claude Code process, such as `claude` in a terminal or another VS Code window, a notice appears in place of the prompt box: `This conversation is still open somewhere else. Using it in two places at once can mix up its messages.` To continue here, close the conversation in the other place and then click **Open here anyway**. If you click without closing it, the conversation is open in both places. With [`claudeProcessWrapper`](#extension-settings) set, the extension skips this check and opens the conversation directly.
207
206208By default, a session with no activity for 14 days moves to **Archived sessions** automatically, unless it is open, unread, or in a [group](#organize-sessions-into-groups). Automatic archiving requires Claude Code v2.1.265 or later. To change the period or turn it off, open the [Archive Inactive Sessions setting](vscode://settings/claudeCode.archiveInactiveSessions) and select a number of days or **Never**.
207209
208210To restore an archived session, expand **Archived sessions** and click **Unarchive session**. To restore every archived session at once, hover over the **Archived sessions** header in the sessions list in the Activity Bar and click its unarchive icon, which requires Claude Code v2.1.277 or later. Before v2.1.257, the action was **Delete session**, which hid a session with no way to restore it. Sessions you deleted then appear under **Archived sessions** after you upgrade.
from line 275
273275 Use the sidebar for your main Claude session and open additional tabs for side tasks. Claude remembers your preferred location. The Activity Bar sessions list icon is separate from the Claude panel: the sessions list is always visible in the Activity Bar, while the Claude panel icon only appears there when the panel is docked to the left sidebar.
274276</Tip>
275277
278### Continue conversations after a reload
279
276280After you run **Developer: Reload Window** or restart VS Code, whether a chat comes back with its conversation depends on where it was open:
277281
278282* **Editor tab**: the conversation comes back with its tab.
279283* **Sidebar**: the conversation comes back if you sent a message or Claude responded in it within the last 10 minutes. If it doesn't come back, resume the conversation from [Session history](#resume-past-conversations).
280284
285If another Claude Code process still has the conversation open, you're asked before it opens here, with the same **Open here anyway** notice as when you [resume it from session history](#resume-past-conversations).
286
281287If the reload interrupted Claude mid-step, Claude continues that step when the conversation comes back, and a notice in the chat marks the continuation. Requires Claude Code v2.1.274 or later. If the step was interrupted more than an hour ago or the session is open elsewhere, the conversation comes back idle instead.
282288
283To turn continuation off, open the [Continue After Reload setting](vscode://settings/claudeCode.continueAfterReload) and uncheck it.
289To turn continuation off, open the [Continue After Reload setting](vscode://settings/claudeCode.continueAfterReload) and uncheck it. Setting [`CLAUDE_CODE_RESUME_INTERRUPTED_TURN`](/docs/en/env-vars#variables) or any other `CLAUDE_CODE_RESUME_` variable in VS Code's environment or in the [`environmentVariables` setting](#extension-settings) has no effect in the panel, because the extension removes those variables before it starts the panel's sessions.
284290
285291### Run multiple conversations
286292
from line 524
518524| `enableNewConversationShortcut` | `false` | Enable Cmd/Ctrl+N to start a new conversation |
519525| `enableReopenClosedSessionShortcut` | `true` | Use Cmd/Ctrl+Shift+T to reopen the most recently closed Claude session tab. When the last closed tab wasn't a Claude session, the shortcut runs VS Code's normal reopen-closed-editor command instead. |
520526| `archiveInactiveSessions` | `14` | [Archive a session automatically](#resume-past-conversations) after this many days without activity: `1`, `2`, `7`, or `14`. Set `0` to turn it off. Requires Claude Code v2.1.265 or later |
521| `continueAfterReload` | `true` | After a window reload, Claude [continues the step that was interrupted](#choose-where-claude-lives) in the restored session. Requires Claude Code v2.1.274 or later |
527| `continueAfterReload` | `true` | After a window reload, Claude [continues the step that was interrupted](#continue-conversations-after-a-reload) in the restored session. Requires Claude Code v2.1.274 or later |
522528| `hideOnboarding` | `false` | Hide the onboarding checklist (graduation cap icon) |
523529| `focusView` | `false` | Hide tool calls, tool results, and thinking behind expandable rows, leaving your prompts and Claude's responses. Claude's latest to-do list stays visible; this requires Claude Code v2.1.225 or later. You can also toggle Focus view from the command menu. Requires Claude Code v2.1.221 or later |
524530| `respectGitIgnore` | `true` | Exclude .gitignore patterns from file searches and from [selection context](#reference-files-and-folders) |
from line 604
598604
599605Reference terminal output in your prompts using `@terminal:name` where `name` is the terminal's title. This lets Claude see command output, error messages, or logs without copy-pasting.
600606
607### Move a running command or subagent to the background
608
609When Claude is waiting on a command or a [subagent](/docs/en/sub-agents) that is taking longer than you want, click **Run in background** below its tool call in the conversation. The action appears once a command has been running for about two seconds, or as soon as a subagent starts. Claude stops waiting and continues the turn, while the command or subagent keeps running as a [background task](/docs/en/tools-reference#background-commands) that notifies Claude when it finishes. Requires Claude Code v2.1.287 or later.
610
611To check on the task or stop it in the meantime, type `/tasks` in the prompt box to open the [agent map](#use-the-prompt-box). A subagent keeps its place in the tree of agents there, and a command is listed below the agents with its [latest output on its card](#monitor-background-processes). A command you move to the background this way is subject to the [time limit for background commands](/docs/en/tools-reference#time-limit-for-background-commands).
612
601613### Monitor background processes
602614
603Type `/tasks` in the prompt box to open the [agent map](#use-the-prompt-box), which lists the session's background tasks, such as a dev server Claude left running as a background shell command. Click a task to open its card and stop it there. Requires Claude Code v2.1.277 or later.
615Type `/tasks` in the prompt box to open the [agent map](#use-the-prompt-box), which lists the session's background tasks, such as a dev server Claude left running as a background shell command. Click a task to open its card, where you can stop it. Requires Claude Code v2.1.277 or later.
616
617For a background shell command, or a [monitor](/docs/en/tools-reference#monitor-tool) that runs a command, the card also shows the command's latest output and refreshes it while the command runs.
604618
605619### Connect to external tools with MCP
606620
cloud-environments Changed · +1 / -1 lines
from line 235
235235
236236* **Git credentials**: the git client inside the VM uses a scoped credential, which the proxy verifies and swaps for your actual GitHub token.
237237* **API requests**: requests from the built-in GitHub tools, and from `gh` under the [`proxy-injected` placeholder](#work-with-github-issues-and-pull-requests), go out with your real credentials substituted.
238* **Push protection**: `git push` works only against the session's current working branch; cloning, fetching, and PR operations work normally.
238* **Push restrictions**: the proxy rejects branch deletions and pushes of anything other than a branch, such as a tag. It doesn't limit which branches a push can update. To do that, use branch protection rules or rulesets on GitHub.
239239* **Repository scope**: GitHub API and release-asset requests reach only repositories attached to the session, so a setup script that downloads release assets from an unattached repository gets a 403.
240240* **GraphQL restrictions**: the proxy serves only a pinned set of GraphQL operations for pull-request workflows. The proxy rejects everything else on the GraphQL endpoint with a 403 that says `This GraphQL query is not enabled for this session` and names the REST fallback, `gh api repos/{owner}/{repo}/...`. The restriction applies to every request through the proxy regardless of the credentials you supply, so a `GH_TOKEN` you set gets the same 403. Claude can't reach GitHub APIs that exist only in GraphQL, such as Projects v2, through the proxy.
241241
errors 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.
from line 509
509509* `Connection lost mid-response`: the connection dropped. You also see this variant when a proxy or gateway ends the response body cleanly before the response has finished.
510510* `Your computer went to sleep mid-response`: Claude Code detected that your computer went to sleep while the response was streaming. Once your computer wakes, Claude Code treats the connection as broken and stops reading from it.
511511* `Part of the response never arrived`: a stream event was dropped between the API and Claude Code, so a later event referenced content that never arrived. Before v2.1.281, this case ended the turn with `API Error: Content block not found`.
512* `The response stream was malformed`: an event arrived for a content block that had already finished, or an event arrived damaged. A damaged event is one whose data isn't valid JSON, whose content is missing, or whose content doesn't match the event's type. Before v2.1.284, the parser's raw error, such as one beginning `API Error: JSON Parse error`, appeared instead when an event with invalid JSON arrived after Claude had completed its thinking, a block of text, or a tool call. Before v2.1.287, when an [Amazon Bedrock guardrail](/docs/en/amazon-bedrock#aws-guardrails) blocked a response that had already streamed thinking and some text, this variant appeared in place of the guardrail's message.
512* `The response stream was malformed`: an event arrived for a content block that had already finished, or an event arrived damaged. A damaged event is one whose data isn't valid JSON, whose content is missing, or whose content doesn't match the event's type. Before v2.1.284, the parser's raw error, such as one beginning `API Error: JSON Parse error`, appeared instead when an event with invalid JSON arrived after Claude had completed its thinking, a block of text, or a tool call.
513513* `The response stopped arriving`: the connection stayed open but stopped delivering data, so the streaming idle watchdog aborted it. Before v2.1.222, Claude Code could also report this failure on [gateway](/docs/en/gateways) connections reached through `ANTHROPIC_BASE_URL` or `ANTHROPIC_AWS_BASE_URL` while the server's keep-alive pings were still arriving, because it counted only parsed response events there; upgrading stops those spurious timeouts on those routes. Gateways reached through a provider base URL such as `ANTHROPIC_BEDROCK_BASE_URL` aren't wrapped by the byte watchdog; see [Streaming idle watchdogs](/docs/en/network-config#streaming-idle-watchdogs).
514514
515515Before v2.1.227, `Connection lost mid-response` read `Connection closed mid-response` and `The response stopped arriving` read `Response stalled mid-stream`.
from line 2826
28262826error: The current working directory was deleted, so that command didn't work. Please cd into a different directory and try again.
28272827```
28282828
2829The cause and the fix are the same fo
2829The cause and the fix are the same for both forms.
2830
2831When Claude Code can't read the working directory for a different reason, such as a permissions change, the message names the error code instead: `Can't read the current directory (EACCES). Start Claude Co
permission-modes Changed · +2 / -1 lines
from line 489
489489 2. Read-only actions and file edits in your working directory are auto-approved, except writes to [protected paths](#protected-paths) and [the first read outside the working directories](#first-read-outside-the-working-directories), which prompts you
490490 * In a session with [server-side classifier review](#server-side-classifier-review), read-only and [sandboxed](/docs/en/sandboxing#sandbox-modes) shell commands wait for that review and are blocked if it flags them
491491 * A write inside your working directory that the [symlink check](/docs/en/permissions#symlinks) resolves to a location outside it prompts you
492 * When Claude reads an [artifact someone else made](/docs/en/artifacts#read-an-artifact-shared-with-you), the approval cases listed in that section apply
492493 3. Everything else goes to the classifier, apart from [critical-path removals](#critical-paths) under their default handling. The connector tools and `requiresUserInteraction` MCP tools that prompt you directly in step 1 never reach the classifier either, so neither an org-required approval nor a consent step is auto-approved
493494 4. If the classifier blocks, Claude receives the reason. In most sessions the reason names the rule the classifier matched, such as `[Data Exfiltration]`, rather than giving a written explanation; see [Review denials](/docs/en/auto-mode-config#review-denials)
494495
from line 553
552553
553554`bypassPermissions` mode disables permission prompts and safety checks so tool calls execute immediately, including writes to [protected paths](#protected-paths).
554555
555The [actions no mode auto-approves](#actions-no-mode-auto-approves) still prompt in this mode. The [Remove-Item in PowerShell](#remove-item-in-powershell) denies also apply in this mode.
556The [actions no mode auto-approves](#actions-no-mode-auto-approves) still prompt in this mode. Reading [another organization's public artifact](/docs/en/artifacts#read-an-artifact-shared-with-you) needs your approval, and this mode doesn't ask for it, so Claude can't read one. The [Remove-Item in PowerShell](#remove-item-in-powershell) denies also apply in this mode.
556557
557558Two [cross-session messaging](/docs/en/cross-session-messaging) safeguards still apply in this mode, and in interactive terminal plan-mode sessions where bypass permissions are available:
558559
security Changed · +1 / -1 lines
from line 97
9797* **Isolated virtual machines**: Each cloud session runs in an isolated, Anthropic-managed VM
9898* **Network access controls**: Network access is limited by default and can be configured to be disabled or allow only specific domains
9999* **Credential protection**: GitHub credentials are stored encrypted on Anthropic's servers and never enter the session VM. The VM holds a short-lived credential scoped to that session, and GitHub traffic goes through an [Anthropic proxy](/docs/en/cloud-environments#github-proxy) that attaches the GitHub credential on the server side. See [GitHub authentication options](/docs/en/claude-code-on-the-web#github-authentication-options) for how you grant access
100* **Branch restrictions**: Git push operations are restricted to the current working branch
100* **Push restrictions**: The [GitHub proxy](/docs/en/cloud-environments#github-proxy) rejects branch deletions and pushes of anything other than a branch, such as a tag. GitHub decides which branches a session can update by applying your repository's branch protection rules and rulesets to the GitHub access you connected. A rule that access can bypass doesn't block a session's push
101101* **Audit logging**: All operations in cloud sessions are logged for compliance and audit purposes
102102* **Automatic cleanup**: Session VMs are reclaimed after a period of inactivity
103103* **Deletion**: You can [delete a session](/docs/en/claude-code-on-the-web#delete-sessions) at any time. See [Cloud execution data flow](/docs/en/data-usage#cloud-execution-data-flow-and-dependencies) for what Anthropic stores for a cloud session
tools-reference Changed · +2 / -0 lines
from line 583
583583
584584An explicit `WebFetch(domain:...)` rule in `deny`, `ask`, or `allow` takes precedence over the preapproved set, so you can block a preapproved domain or require a prompt for it.
585585
586When the URL is a claude.ai [artifact](/docs/en/artifacts) link, Claude Code can also ask for approval to read the artifact itself. For the cases where it asks, see [Read an artifact shared with you](/docs/en/artifacts#read-an-artifact-shared-with-you).
587
586588WebFetch sets a `User-Agent` header beginning with `Claude-User`, and an `Accept` header that prefers Markdown over HTML so servers that support content negotiation can return Markdown directly.
587589
588590Sandboxed commands don't inherit WebFetch's built-in set of preapproved documentation domains. To let a sandboxed command reach a domain without a prompt, add the domain to [`allowedDomains`](/docs/en/settings-reference#sandbox-network-alloweddomains) or allow it with a `WebFetch(domain:...)` rule, which the [sandbox also honors](/docs/en/sandboxing#network-isolation). WebFetch never reads the sandbox allowlist in return, so adding a domain to a sandbox or organization network allowlist doesn't stop WebFetch from prompting for it.