HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
808pages tracked
587 changed this week · last read 22 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 22 Oct 2026
Claude Documentation
278pages tracked
74 changed this week · last read 22 Oct 2026
Model Context Protocol
357pages tracked
163 changed this week · last read 21 Oct 2026
100 on this page
5,287 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
14 Oct 2026
69 pages
+2181 −1697 lines
claude-code
llm-gateway-protocol
±changed
+2−1
claude-codechanged
llm-gateway-protocol
* On a direct connection, or through a gateway set with `ANTHROPIC_BASE_URL`, Claude Code keeps sending the tool-search beta header, `defer_loading` tool fields, and `tool_referenc
* On a direct connection without the HIPAA configuration, or through a gateway set with `ANTHROPIC_BASE_URL`, Claude Code keeps sending the tool-search beta header, `defer_loading`
* In a session that [gets the HIPAA configuration](/docs/en/hipaa-setup#check-how-developers-sign-in-and-connect), the override has no effect and tool search stays off
+2 −1 lines
Upstream edited 14 Oct 2026 02:42 UTC Recorded here 14 Oct 2026 03:07 UTC
claude-code
hipaa-setup
±changed
+1−0
claude-codechanged
hipaa-setup
| MCP tools load into context upfront | [MCP tool search](/docs/en/mcp#configure-tool-search) is off. Neither `ENABLE_TOOL_SEARCH` nor managed settings turns it back on |
+1 −0 lines
Upstream edited 14 Oct 2026 02:42 UTC Recorded here 14 Oct 2026 03:07 UTC
claude-code
agent-sdk/tool-search
±changed
+1−1
claude-codechanged
agent-sdk/tool-search
Setting [`CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS`](/docs/en/env-vars) keeps tool search off. You can't override it by setting `ENABLE_TOOL_SEARCH` yourself. Your organization can k
Setting [`CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS`](/docs/en/env-vars) keeps tool search off. You can't override it by setting `ENABLE_TOOL_SEARCH` yourself. On Claude Code v2.1.227
+1 −1 lines
Upstream edited 14 Oct 2026 02:42 UTC Recorded here 14 Oct 2026 03:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 14 Oct 2026 02:37 UTC
claude-code
microsoft-foundry
±changed
+12−79
claude-codechanged
microsoft-foundry
export const ContactSalesCard = ({surface}) => {
const utm = content => `utm_source=claude_code&utm_medium=docs&utm_content=${surface}_${content}`;
const iconArrowRight = (size = 13) => <svg width={size} height={size} viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5" strokeLinecap="round" strokeLinejoin
<line x1="5" y1="12" x2="19" y2="12" />
<polyline points="12 5 19 12 12 19" />
+12 −79 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
google-vertex-ai
±changed
+30−99
claude-codechanged
google-vertex-ai
export const ContactSalesCard = ({surface}) => {
const utm = content => `utm_source=claude_code&utm_medium=docs&utm_content=${surface}_${content}`;
const iconArrowRight = (size = 13) => <svg width={size} height={size} viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5" strokeLinecap="round" strokeLinejoin
<line x1="5" y1="12" x2="19" y2="12" />
<polyline points="12 5 19 12 12 19" />
+30 −99 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
claude-platform-on-aws
±changed
+6−188
claude-codechanged
claude-platform-on-aws
export const ContactSalesCard = ({surface}) => {
const utm = content => `utm_source=claude_code&utm_medium=docs&utm_content=${surface}_${content}`;
const iconArrowRight = (size = 13) => <svg width={size} height={size} viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5" strokeLinecap="round" strokeLinejoin
<line x1="5" y1="12" x2="19" y2="12" />
+6 −188 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
workflows
±changed
+3−3
claude-codechanged
workflows
| `Esc` or `←` | Back out one level. In v2.1.203 through v2.1.205, `←` didn't step back out of a phase or agent; use `Esc` on those versions |
| `Esc` or `←` | Back out one level |
To start a session with ultracode already on, launch with `claude --effort ultracode`, which also sets the effort level to `xhigh`. Requires Claude Code v2.1.203 or later.
To start a session with ultracode already on, launch with `claude --effort ultracode`, which also sets the effort level to `xhigh`.
A size guideline tells Claude how many agents to aim for when it writes a dynamic workflow. Claude Code sends the guideline to Claude as advice, not a cap, so a prompt that calls f
+3 −3 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
tools-reference
±changed
+3−3
claude-codechanged
tools-reference
| `ScheduleWakeup` | Reschedules the next iteration of a [self-paced `/loop`](/docs/en/scheduled-tasks#let-claude-choose-the-interval). Claude calls this at the end of each iterati
| `ScheduleWakeup` | Reschedules the next iteration of a [self-paced `/loop`](/docs/en/scheduled-tasks#let-claude-choose-the-interval). Claude calls this at the end of each iterati
| `TaskOutput` | Retrieves output from a background task. Deprecated in favor of `Read` on the task's output file path. When no task matches the ID, the error lists the running bac
| `TaskStop` | Stops a running background task by ID. It also accepts an [agent-team teammate](/docs/en/agent-teams) or a named background agent by agent ID or name. When no task m
| `TaskOutput` | Removed in v2.1.277. Previously retrieved output from a background task; Claude reads a background task's [output file](/docs/en/interactive-mode#how-backgrounding
+3 −3 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
sub-agents
±changed
+4−4
claude-codechanged
sub-agents
Keep `name` values unique across the whole tree: if two files under the same `.claude/agents/` directory, including its subfolders, declare the same name, Claude Code loads only on
Keep `name` values unique across the whole tree: if two files under the same `.claude/agents/` directory, including its subfolders, declare the same name, Claude Code loads only on
A subagent with `isolation: worktree` runs its Bash and PowerShell commands inside its worktree. A command whose working directory resolves to your main checkout instead, for examp
A subagent with `isolation: worktree` runs its Bash and PowerShell commands inside its worktree. A command whose working directory resolves to your main checkout instead, for examp
* **Sibling roster**: a [system reminder](/docs/en/glossary#system-reminder) listing `main` and every other named agent in the session, each a valid `to` value for [`SendMessage`](
+4 −4 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
statusline
±changed
+2−2
claude-codechanged
statusline
| `model` | string, optional | ID of the resolved model the task runs on. Omitted until the model is resolved. Requires Claude Code v2.1.205 or later |
| `model` | string, optional | ID of the resolved model the task runs on. Omitted until the model is resolved |
| `contextWindowSize` | number, optional | Context window of `model` in tokens, computed the same way as the main status line's [`context_window.context_window_size`](#context-wind
| `contextWindowSize` | number, optional | Context window of `model` in tokens, computed the same way as the main status line's [`context_window.context_window_size`](#context-wind
+2 −2 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
skills
±changed
+2−2
claude-codechanged
skills
The [`/doctor`](/docs/en/commands#all-commands) setup checkup stays typable when `disableBundledSkills` is on, in Claude Code v2.1.205 and later. To hide it, set the `DISABLE_DOC
The [`/doctor`](/docs/en/commands#all-commands) setup checkup stays typable when `disableBundledSkills` is on. To hide it, set the `DISABLE_DOCTOR_COMMAND` environment variable o
Claude edits the recorded file only when it steered a run wrong, such as a command that failed or a missing step, so you can commit the file without per-session diffs. Before v2.1.
Claude edits the recorded file only when it steered a run wrong, such as a command that failed or a missing step, so you can commit the file without per-session diffs.
+2 −2 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
setup
±changed
+6−6
claude-codechanged
setup
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme=
```batch theme={null}
+6 −6 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
settings-reference
±changed
+3−3
claude-codechanged
settings-reference
* **Per-session overrides**: `/effort ultracode` turns ultracode on for one session without this key, and `/effort ultracode off` turns it off for one session when this key is `tru
* **Per-session overrides**: `/effort ultracode` turns ultracode on for one session without this key, and `/effort ultracode off` turns it off for one session when this key is `tru
Claude Code ignores project and local entries because it substitutes these values into plugin hook, MCP, and LSP configurations, and a cloned repository must not be able to supply
Claude Code ignores project and local entries because it substitutes these values into plugin hook, MCP, and LSP configurations, and a cloned repository must not be able to supply
Outside a git repository, a [`WorktreeCreate` hook](/docs/en/worktrees#non-git-version-control) that fails releases the block so the session can edit the working directory in place
+3 −3 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
permissions
±changed
+1−3
claude-codechanged
permissions
When you approve a file path with "Yes, and don't ask again", Claude Code escapes gitignore pattern characters in that path, such as `[`, `]`, and `*`, so the generated rule matche
When you approve a file path with "Yes, and don't ask again", Claude Code escapes gitignore pattern characters in that path, such as `[`, `]`, and `*`, so the generated rule matche
Before v2.1.207, Claude Code applied an untracked file's rules before you accepted the dialog.
+1 −3 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
permission-modes
±changed
+5−14
claude-codechanged
permission-modes
* Before v2.1.202, sessions connected with `/remote-control` or `claude --remote-control` didn't report their permission mode at all, so claude.ai and the mobile app could sh
In v2.1.158 through v2.1.206, auto mode was off on these providers until you set `CLAUDE_CODE_ENABLE_AUTO_MODE=1`, and Claude Code ignored `defaultMode: "auto"` on these providers
* Including sensitive details in content sent, uploaded, published, or written to other people or shared systems, when your own message didn't authorize those details for that reci
* Including sensitive details in content sent, uploaded, published, or written to other people or shared systems, when your own message didn't authorize those details for that reci
+5 −14 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
monitoring-usage
±changed
+2−2
claude-codechanged
monitoring-usage
* `workflow.run_id`: run identifier, prefixed `wf_`, on the API and tool events emitted by agents that belong to a [Workflow](/docs/en/workflows) tool run. Filtering events by one
* `workflow.name`: name of the workflow, its script's `meta.name`, emitted alongside `workflow.run_id`. Built-in workflow names appear verbatim when the run executes the unmodified
* `workflow.run_id`: run identifier, prefixed `wf_`, on the API and tool events emitted by agents that belong to a [Workflow](/docs/en/workflows) tool run. Filtering events by one
* `workflow.name`: name of the workflow, its script's `meta.name`, emitted alongside `workflow.run_id`. Built-in workflow names appear verbatim when the run executes the unmodified
+2 −2 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
microsoft-foundry
±changed
+1−1
claude-codechanged
microsoft-foundry
Claude Code sends the value of `ANTHROPIC_FOUNDRY_AUTH_TOKEN` on every request as the `Authorization: Bearer` header. Use this option when another process, such as a host applicati
Claude Code sends the value of `ANTHROPIC_FOUNDRY_AUTH_TOKEN` on every request as the `Authorization: Bearer` header. Use this option when another process, such as a host applicati
+1 −1 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
memory
±changed
+2−2
claude-codechanged
memory
Glob syntax treats `[` as the start of a bracket expression such as `[abc]`. A pattern with a `[` that can't be read as a bracket expression, such as `photos [2024/**`, is invalid:
Glob syntax treats `[` as the start of a bracket expression such as `[abc]`. A pattern with a `[` that can't be read as a bracket expression, such as `photos [2024/**`, is invalid:
The [`/doctor`](/docs/en/commands#all-commands) checkup proposes trims for a checked-in CLAUDE.md: it cuts content Claude can derive from the codebase, such as directory layouts, d
The [`/doctor`](/docs/en/commands#all-commands) checkup proposes trims for a checked-in CLAUDE.md: it cuts content Claude can derive from the codebase, such as directory layouts, d
+2 −2 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
mcp
±changed
+7−7
claude-codechanged
mcp
A JSON entry that has a `url` but no `type` is a configuration error, because Claude Code reads an entry with no `type` as a stdio server. Claude Code skips that server and reports
A JSON entry that has a `url` but no `type` is a configuration error, because Claude Code reads an entry with no `type` as a stdio server. Claude Code skips that server and reports
`CLAUDE_PROJECT_DIR` is the stable project root and doesn't change when you add or remove working directories mid-session. A server that limits its own filesystem access to a set o
`CLAUDE_PROJECT_DIR` is the stable project root and doesn't change when you add or remove working directories mid-session. A server that limits its own filesystem access to a set o
A per-server `timeout` of at least 1000 also acts as a floor on the idle timeout described below: Claude Code never aborts that server's tool calls for idleness sooner than the per
+7 −7 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
llm-gateway-connect
±changed
+1−1
claude-codechanged
llm-gateway-connect
For a gateway that injects its own `Authorization` header, set `CLAUDE_CODE_SKIP_FOUNDRY_AUTH=1` and leave both credential variables unset. Claude Code then sends requests without
For a gateway that injects its own `Authorization` header, set `CLAUDE_CODE_SKIP_FOUNDRY_AUTH=1` and leave both credential variables unset. Claude Code then sends requests without
+1 −1 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
large-codebases
±changed
+1−1
claude-codechanged
large-codebases
Sparse checkout requires git to enable `extensions.worktreeConfig` in the repository's shared `.git/config` while a sparse worktree exists. Claude Code removes that entry after the
Sparse checkout requires git to enable `extensions.worktreeConfig` in the repository's shared `.git/config` while a sparse worktree exists. Claude Code removes that entry after the
+1 −1 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
hooks
±changed
+5−3
claude-codechanged
hooks
If you press `Esc` in the terminal while `UserPromptSubmit` hooks are still checking a prompt, the text you typed goes back into the prompt box.
| `auto` | Auto-compact when the conversation reaches the [auto-compact window](/docs/en/model-config#set-the-auto-compact-window) |
| `auto` | Auto-compact when the conversation reaches the [auto-compact window](/docs/en/model-config#set-the-auto-compact-window), and [idle compaction](/docs/en/settings-referenc
| `auto` | After auto-compact when the conversation reaches the [auto-compact window](/docs/en/model-config#set-the-auto-compact-window) |
+5 −3 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
headless
±changed
+5−5
claude-codechanged
headless
If the value isn't a valid JSON Schema, `claude` exits with `Error: --json-schema is not a valid JSON Schema` followed by the validator's diagnostic. Claude Code accepts schemas th
If the value isn't a valid JSON Schema, `claude` exits with `Error: --json-schema is not a valid JSON Schema` followed by the validator's diagnostic. Claude Code accepts schemas th
* [`hook_started`, `hook_progress`, and `hook_response` events](/docs/en/agent-sdk/typescript#sdkhookstartedmessage), while a configured [`SessionStart`](/docs/en/hooks#sessionstar
The event also carries an optional `capabilities` array of strings naming the protocol behaviors this Claude Code version implements, such as `interrupt_receipt_v1` or `interrupt_c
+5 −5 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
google-vertex-ai
±changed
+2−2
claude-codechanged
google-vertex-ai
Opus models have a higher per-token price than Sonnet models, so a deployment that doesn't pin a primary model is billed at the Opus rate once it updates to v2.1.207 or later. To
Opus models have a higher per-token price than Sonnet models, so if you don't pin a primary model, you're billed at the Opus rate. To use Sonnet 4.5 as the primary model, set `AN
Before v2.1.280, the primary model on Google Cloud's Agent Platform defaulted to Opus 5 and the `opus` alias resolved to Opus 5 from v2.1.219. On v2.1.207 through v2.1.218, the pri
Before v2.1.280, the primary model on Google Cloud's Agent Platform defaulted to Opus 5 and the `opus` alias resolved to Opus 5 from v2.1.219. On v2.1.207 through v2.1.218, the pri
+2 −2 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
feature-availability
±changed
+1−1
claude-codechanged
feature-availability
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5 or later, Opus 4.7 or late
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5 or later, Opus 4.7 or late
+1 −1 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
desktop
±changed
+1−1
claude-codechanged
desktop
You can send a command while Claude is working, the same as any other message, and the session returns to idle once the turn finishes. Before v2.1.206, a command sent mid-turn coul
You can send a command while Claude is working, the same as any other message, and the session returns to idle once the turn finishes.
+1 −1 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
claude-platform-on-aws
±changed
+1−1
claude-codechanged
claude-platform-on-aws
The default aliases `fable`, `opus`, `sonnet`, and `haiku` resolve to Claude Code's built-in defaults for Claude Platform on AWS, which can lag the newest release. Without `ANTHROP
The default aliases `fable`, `opus`, `sonnet`, and `haiku` resolve to Claude Code's built-in defaults for Claude Platform on AWS, which can lag the newest release. Without `ANTHROP
+1 −1 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
claude-code-on-the-web
±changed
+1−1
claude-codechanged
claude-code-on-the-web
* **`/model`, `/effort`, `/color`, and `/rename`**: pass the value as an argument, for example `/model sonnet`, instead of opening the terminal picker or slider. The argument forms
* **`/model`, `/effort`, `/color`, and `/rename`**: pass the value as an argument, for example `/model sonnet`, instead of opening the terminal picker or slider. The argument forms
+1 −1 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
claude-apps-gateway-config
±changed
+1−1
claude-codechanged
claude-apps-gateway-config
A [non-interactive run](/docs/en/server-managed-settings#security-approval-dialogs), such as `claude -p`, an Agent SDK session, or a session in Claude Desktop's Code tab, can't sho
A [non-interactive run](/docs/en/server-managed-settings#security-approval-dialogs), such as `claude -p`, an Agent SDK session, or a session in Claude Desktop's Code tab, can't sho
+1 −1 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
amazon-bedrock
±changed
+4−4
claude-codechanged
amazon-bedrock
Claude Code resolves the AWS default credential provider chain once and keeps the resolved credentials in memory. It reuses them until five minutes before they expire, or for one h
Claude Code resolves the AWS default credential provider chain once and keeps the resolved credentials in memory. It reuses them until five minutes before they expire, or for one h
When you configure `awsCredentialExport` without `awsAuthRefresh`, Claude Code uses the exported credentials directly and doesn't re-resolve the AWS default credential provider cha
When you configure `awsCredentialExport` without `awsAuthRefresh`, Claude Code uses the exported credentials directly and doesn't re-resolve the AWS default credential provider cha
Opus models have a higher per-token price than Sonnet models, so a deployment that doesn't pin a primary model is billed at the Opus rate once it updates to v2.1.207 or later. To
+4 −4 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
agent-teams
±changed
+1−1
claude-codechanged
agent-teams
Each agent's mailbox is a JSON file at `~/.claude/teams/{team-name}/inboxes/{agent-name}.json`. Claude Code validates every entry when it reads a mailbox file. Entries that don't m
Each agent's mailbox is a JSON file at `~/.claude/teams/{team-name}/inboxes/{agent-name}.json`. Claude Code validates every entry when it reads a mailbox file. Entries that don't m
+1 −1 lines
Upstream edited 14 Oct 2026 02:36 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
prompt-caching
±changed
+2−0
claude-codechanged
prompt-caching
If you leave a long conversation idle in a terminal session while it is on the [one-hour TTL](#which-ttl-each-request-gets), Claude Code can compact it shortly before the cache exp
+2 −0 lines
Upstream edited 14 Oct 2026 02:34 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
llm-gateway-protocol
±changed
+1−1
claude-codechanged
llm-gateway-protocol
| `x-claude-code-compaction` | Present on the request that summarizes the conversation during a [compaction](/docs/en/prompt-caching#compacting-the-conversation). The value says wh
| `x-claude-code-compaction` | Present on the request that summarizes the conversation during a [compaction](/docs/en/prompt-caching#compacting-the-conversation). The value says wh
+1 −1 lines
Upstream edited 14 Oct 2026 02:34 UTC Recorded here 14 Oct 2026 02:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 14 Oct 2026 02:07 UTC
claude-code
corporate-launcher
±changed
+1−0
claude-codechanged
corporate-launcher
* **Run `exec` from the directory the launcher started in.** Claude Code works in the directory it starts in, so a launcher that changes directory can start a session in the wrong
+1 −0 lines
Upstream edited 14 Oct 2026 01:59 UTC Recorded here 14 Oct 2026 02:07 UTC
claude-code
plugins/dependencies
±changed
+9−11
claude-codechanged
plugins/dependencies
<Note>
These cases are covered on other pages:
* **Installing a plugin that has dependencies**: see [Manage installed plugins](/docs/en/plugins/install#manage-installed-plugins)
* **Reading a dependency error**: see [Dependency errors](/docs/en/plugins/troubleshooting#dependency-errors)
+9 −11 lines
Upstream edited 14 Oct 2026 01:58 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
plugins/troubleshooting
±changed
+2−1
claude-codechanged
plugins/troubleshooting
| `"<name>@synced" is loaded from your claude.ai account but meets a marketplace dependency only for other claude.ai plugins`, inside the `is not installed` message | The dependenc
To see these programmatically, run `claude plugin list --json` in your shell. Plugins with problems carry an `errors` field with the messages and an `errorDetails` field with a `ty
To see these programmatically, run `claude plugin list --json` in your shell. Plugins with problems carry an `errors` field with the messages and an `errorDetails` field with a `ty
+2 −1 lines
Upstream edited 14 Oct 2026 01:58 UTC Recorded here 14 Oct 2026 02:07 UTC
claude-code
plugins/dependencies
±changed
+11−0
claude-codechanged
plugins/dependencies
### Dependencies when your plugin loads from claude.ai
When a user turns your plugin on for their claude.ai account, Claude Code loads it as `<name>@synced`, [with no marketplace](/docs/en/plugins/loading#synced-plugins). For that copy
* **The dependency from its marketplace**: installed from the marketplace your entry names, and enabled. Claude Code checks a `version` range in your entry against the installed co
+11 −0 lines
Upstream edited 14 Oct 2026 01:58 UTC Recorded here 14 Oct 2026 02:07 UTC
claude-code
agent-sdk/typescript
±changed
+14−4
claude-codechanged
agent-sdk/typescript
claude_code_version?: string;
`claude_code_version` is the Claude Code version of the process that runs the session's turns. It is the same value the [`SDKSystemMessage`](#sdksystemmessage) init message carries
* The field requires Agent SDK v0.3.296 or later, which bundles Claude Code v2.1.296.
+14 −4 lines
Upstream edited 14 Oct 2026 01:57 UTC Recorded here 14 Oct 2026 02:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 14 Oct 2026 01:37 UTC
claude-code
debug-your-config
±changed
+39−45
claude-codechanged
debug-your-config
<Note>
CLAUDE.md and permissions solve different problems. CLAUDE.md tells Claude how your project works so it makes good decisions. [Permissions](/docs/en/permissions) and [hooks](/doc
</Note>
> [!NOTE]
>
+39 −45 lines
Upstream edited 14 Oct 2026 01:27 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
sub-agents
±changed
+3−3
claude-codechanged
sub-agents
Explore and Plan skip your CLAUDE.md files and the git status snapshot to keep research fast and inexpensive. Every other built-in and [custom subagent](#configure-subagents) loads
Explore and Plan start without your CLAUDE.md files and the git status snapshot to keep research fast and inexpensive. Other built-in and [custom subagents](#configure-subagents) l
| `omitClaudeMd` | No | Set to `true` to launch this subagent without the user, project, and local CLAUDE.md files; [managed policy files](/docs/en/memory#how-claude-md-files-load)
| `omitClaudeMd` | No | Set to `true` to start this subagent without the user, project, and local CLAUDE.md files in its [initial context](#what-loads-at-startup); [managed policy
To launch one of your own subagents without the user, project, and local CLAUDE.md files, set [`omitClaudeMd: true`](#supported-frontmatter-fields) in its frontmatter or `--agents`
+3 −3 lines
Upstream edited 14 Oct 2026 01:27 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
skills
±changed
+3−1
claude-codechanged
skills
With `context: fork`, you write the task in your skill and pick an agent type to execute it. The built-in Explore and Plan agents [skip CLAUDE.md and git status](/docs/en/sub-agent
With `context: fork`, you write the task in your skill and pick an agent type to execute it. The built-in Explore and Plan agents [start without CLAUDE.md and git status](/docs/en/
For the inverse, where you define a custom subagent that uses skills as reference material, see [Subagents](/docs/en/sub-agents#preload-skills-into-subagents).
+3 −1 lines
Upstream edited 14 Oct 2026 01:27 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
memory
±changed
+1−1
claude-codechanged
memory
* **Inside each `AGENTS.md`**: [`@path` imports](#import-additional-files) are expanded, [`claudeMdExcludes`](#exclude-specific-claude-md-files) patterns apply, and subagents that
* **Inside each `AGENTS.md`**: [`@path` imports](#import-additional-files) are expanded, [`claudeMdExcludes`](#exclude-specific-claude-md-files) patterns apply, and subagents that
+1 −1 lines
Upstream edited 14 Oct 2026 01:27 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
features-overview
±changed
+1−1
claude-codechanged
features-overview
* CLAUDE.md and git status, except the built-in Explore and Plan agents [omit both](/docs/en/sub-agents#what-loads-at-startup), and an agent whose definition sets [`omitClaudeM
* CLAUDE.md and git status. The built-in Explore and Plan agents [start with neither](/docs/en/sub-agents#what-loads-at-startup), and an agent whose definition sets [`omitClaud
+1 −1 lines
Upstream edited 14 Oct 2026 01:27 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
debug-your-config
±changed
+1−1
claude-codechanged
debug-your-config
| Subagent ignores `CLAUDE.md` instructions | The built-in Explore and Plan agents skip `CLAUDE.md`. A custom subagent loads it the same way the main conversation does, unless its
| Subagent ignores `CLAUDE.md` instructions | The built-in Explore and Plan agents skip `CLAUDE.md` at startup. A custom subagent loads it the same way the main conversation does,
+1 −1 lines
Upstream edited 14 Oct 2026 01:27 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
| `omitClaudeMd` | No | Run this agent without the user, project, and local CLAUDE.md files when it runs as a subagent; managed policy files still load. Use it for agents that take
| `omitClaudeMd` | No | Leave the user, project, and local CLAUDE.md files out of this agent's initial context; managed policy files still load. Use it for agents that take everyth
+1 −1 lines
Upstream edited 14 Oct 2026 01:27 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
agent-sdk/subagents
±changed
+2−2
claude-codechanged
agent-sdk/subagents
| `omitClaudeMd` | `boolean` | No | Run this agent without the user, project, and local CLAUDE.md files when it runs as a subagent; managed policy files still load. Ignored when th
| `omitClaudeMd` | `boolean` | No | Leave the user, project, and local CLAUDE.md files out of this agent's initial context; managed policy files still load. Ignored when the agent
| Project CLAUDE.md (loaded via [`settingSources`](/docs/en/agent-sdk/claude-code-features#control-filesystem-settings-with-settingsources)), unless the agent sets [`omitClaudeMd`]
| Project CLAUDE.md (loaded via [`settingSources`](/docs/en/agent-sdk/claude-code-features#control-filesystem-settings-with-settingsources)). An agent that sets [`omitClaudeMd`](#a
+2 −2 lines
Upstream edited 14 Oct 2026 01:27 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
ultrareview
±changed
+2−2
claude-codechanged
ultrareview
A review typically takes 5 to 10 minutes. The review runs as a background task, so you can keep working in your session or start other commands. If you chose to [post the findings
A review typically takes 15 to 25 minutes. The review runs as a background task, so you can keep working in your session or start other commands. If you chose to [post the findings
| Duration | seconds to a few minutes | roughly 5 to 10 minutes |
| Duration | seconds to a few minutes | roughly 15 to 25 minutes |
+2 −2 lines
Upstream edited 14 Oct 2026 01:14 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
mcp
±changed
+36−11
claude-codechanged
mcp
#### How Claude Code stops a stdio server
When Claude Code disconnects a stdio server, for example when your session ends, it signals the server process and waits briefly for it to exit before forcing it to stop. If your s
+36 −11 lines
Upstream edited 14 Oct 2026 01:12 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
errors
±changed
+20−0
claude-codechanged
errors
| `Tool "mcp__<server>__<tool>" is not sent to Claude: its name has <N> characters and the API accepts at most 128` | [Request errors](#mcp-tool-name-over-128-characters) |
| `tools.N.custom.name: String should have at most 128 characters` | [Request errors](#mcp-tool-name-over-128-characters) |
<h3 id="mcp-tool-name-over-128-characters">
MCP tool name over 128 characters
</h3>
+20 −0 lines
Upstream edited 14 Oct 2026 01:12 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
agent-sdk/tool-search
±changed
+3−3
claude-codechanged
agent-sdk/tool-search
| (unset) | Tool search is on. Tool definitions are deferred and discovered on demand. Falls back to loading upfront on Google Cloud's Agent Platform models earlier than the Claude
| `true` | Tool search is always on, except on a Microsoft Foundry deployment hosted on Azure, where the server-side rejection still forces upfront loading, and on Google Cloud's A
| (unset) | Tool search is on. Tool definitions are deferred and discovered on demand. Falls back to loading upfront on models earlier than Opus 4 and Sonnet 4, Google Cloud's Agen
| `true` | Tool search stays on with a non-first-party `ANTHROPIC_BASE_URL`. The other (unset) fallbacks still apply. The SDK sends the beta header through proxies, and requests fa
* **Model support:** Claude Sonnet 4.5, Claude Haiku 4.5, Claude Opus 4.5, and later models; see [model compatibility in the API docs](https://platform.claude.com/docs/en/agents-an
+3 −3 lines
Upstream edited 14 Oct 2026 01:12 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
agent-sdk/mcp
±changed
+1−1
claude-codechanged
agent-sdk/mcp
After five reconnection attempts fail, the server reports `"failed"`, or `"needs-auth"` when it needs authorizing again. To retry manually, call [`reconnectMcpServer()`](/docs/en/a
After five reconnection attempts fail, the server reports `"failed"`, or `"needs-auth"` when it needs authorizing again. A `"failed"` HTTP or SSE server can still return to `"conne
+1 −1 lines
Upstream edited 14 Oct 2026 01:12 UTC Recorded here 14 Oct 2026 01:37 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 14 Oct 2026 01:07 UTC
claude-code
errors
±changed
+69−7
claude-codechanged
errors
| `Failed to fetch session from Sessions API: Failed to fetch session logs` | [Network](#failed-to-fetch-session-from-sessions-api) |
| `Couldn't verify your organization's policy for cloud sessions` | [Command-line errors](#cloud-sessions-are-disabled-by-your-organizations-policy) |
| `Cloud sessions use your claude.ai login`, at the end of a policy denial that names a credential | [Command-line errors](#cloud-sessions-use-your-claude-ai-login) |
| `Couldn't verify your organization's policy for cloud sessions` | [Command-line errors](#couldnt-verify-your-organizations-policy-for-cloud-sessions) |
| `Cloud sessions aren't available:` followed by why your organization's policy couldn't be loaded | [Command-line errors](#couldnt-verify-your-organizations-policy-for-cloud-sessi
+69 −7 lines
Upstream edited 14 Oct 2026 01:06 UTC Recorded here 14 Oct 2026 01:07 UTC
claude-code
claude-code-on-the-web
±changed
+3−2
claude-codechanged
claude-code-on-the-web
| `Cloud sessions are disabled by your organization's policy. Contact your organization admin to enable them.` | The `allow_remote_sessions` organization policy is off. |
| `Couldn't verify your organization's policy for cloud sessions. Check your network connection and try again.` | Claude Code couldn't fetch your organization's policy, so it refus
| `Cloud sessions are disabled by your organization's policy. Contact your organization admin to enable them.` | Your organization's `allow_remote_sessions` policy is off; see [Clo
| `Couldn't verify your organization's policy for cloud sessions. Check your network connection and try again.` | Claude Code hasn't finished loading your organization's policy, so
| `Cloud sessions aren't available:` followed by a cause | Loading your organization's policy failed, and the rest of the message says how. Act on the cause it names; see [Couldn't
+3 −2 lines
Upstream edited 14 Oct 2026 01:06 UTC Recorded here 14 Oct 2026 01:07 UTC
claude-code
routines
±changed
+5−2
claude-codechanged
routines
API triggers are added to an existing routine from the web. The CLI cannot currently create or revoke tokens.
API triggers are added to an existing routine from the web. The CLI can't currently create, regenerate, or delete tokens.
Each routine has its own token, scoped to triggering that routine only. To rotate or revoke it, return to the same modal and click **Regenerate** or **Revoke**.
Each routine has its own token, scoped to triggering that routine only. To turn off API access or rotate the token, return to the same modal:
+5 −2 lines
Upstream edited 14 Oct 2026 00:08 UTC Recorded here 14 Oct 2026 00:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 14 Oct 2026 00:07 UTC
claude-code
sub-agents
±changed
+1−1
claude-codechanged
sub-agents
Subagents support automatic compaction using the same logic as the main conversation. Compaction triggers under the same conditions, and `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` applies t
Subagents support automatic compaction. Compaction triggers as the subagent's own context window fills, and `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` applies to subagents as well. See [env
+1 −1 lines
Upstream edited 14 Oct 2026 00:07 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
settings-reference
±changed
+45−1
claude-codechanged
settings-reference
| [`idleCompaction`](#idlecompaction) | Stop Claude Code from compacting a long conversation while your terminal session is idle | Memory and context | Any file |
The manual `/compact` command keeps working while auto-compact is off.
The manual `/compact` command keeps working while auto-compact is off. If you turn auto-compact off, [idle compaction](#idlecompaction) turns off too.
### `idleCompaction`
+45 −1 lines
Upstream edited 14 Oct 2026 00:07 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
* `precompute_reuse`: Only set when `trigger` is `"manual"`. Auto-compaction can prepare a summary in the background before the context window fills, and this attribute records whe
* `precompute_reuse`: Only set when `trigger` is `"manual"` or for an [idle compaction](/docs/en/settings-reference#idlecompaction), which reports `trigger` as `"auto"`. Auto-compa
+1 −1 lines
Upstream edited 14 Oct 2026 00:07 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
model-config
±changed
+2−0
claude-codechanged
model-config
See the [`idleCompaction`](/docs/en/settings-reference#idlecompaction) setting for when Claude Code also compacts a conversation you leave idle.
+2 −0 lines
Upstream edited 14 Oct 2026 00:07 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
context-window
±changed
+1−1
claude-codechanged
context-window
Claude Code compacts automatically as you approach the limit, so a full context window doesn't end your session. The automatic pass works the same way as the `/compact` step in the
Claude Code compacts automatically as you approach the limit, so a full context window doesn't end your session. The automatic pass works the same way as the `/compact` step in the
+1 −1 lines
Upstream edited 14 Oct 2026 00:07 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
code-review
±changed
+0−2
claude-codechanged
code-review
If the repository belongs to an organization and your membership in that organization is private, which is GitHub's default, GitHub doesn't identify you to Claude as a member. Clau
+0 −2 lines
Upstream edited 14 Oct 2026 00:00 UTC Recorded here 14 Oct 2026 00:07 UTC
13 Oct 2026
16 pages
+610 −335 lines
claude-code
cloud-environments
±changed
+1−1
claude-codechanged
cloud-environments
* **Repository scope**: the proxy serves GitHub API requests for the repositories attached to the session. An API request for another repository gets a 403 whose message starts wit
* **Repository scope**: the proxy serves GitHub API requests for the repositories attached to the session. An API request for another repository gets a 403 whose message starts wit
+1 −1 lines
Upstream edited 13 Oct 2026 23:57 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
claude-tag
±changed
+65−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+65 −1 lines
Recorded here 13 Oct 2026 20:37 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
* **Local process must keep running**: Remote Control runs as a local process. If you close the terminal, quit the Desktop app or VS Code, or otherwise stop the `claude` process, t
* **Local process must keep running**: Remote Control runs as a local process. If you close the terminal, quit the Desktop app or VS Code that runs the session on your machine, or
+1 −1 lines
Upstream edited 13 Oct 2026 20:19 UTC Recorded here 13 Oct 2026 20:37 UTC
claude-code
desktop-quickstart
±changed
+1−1
claude-codechanged
desktop-quickstart
* **SSH**: Connect to a remote machine over SSH, such as your own servers, cloud VMs, or dev containers. Desktop installs Claude Code on the remote machine automatically the fi
* **SSH**: Connect to a remote machine over SSH, such as your own servers, cloud VMs, or dev containers. Desktop installs Claude Code on the remote machine automatically the fi
+1 −1 lines
Upstream edited 13 Oct 2026 20:19 UTC Recorded here 13 Oct 2026 20:37 UTC
claude-code
desktop
±changed
+163−5
claude-codechanged
desktop
* **Environment**: choose where Claude runs. Select **Local** for your machine, **Cloud** for a [cloud session](#cloud-sessions) that continues after you close the app, an [**SSH c
* **Environment**: choose where Claude runs. Select **Local** for your machine, **Cloud** for a [cloud session](#cloud-sessions) that continues after you close the app, an [**SSH c
The integrated terminal lets you run commands alongside your session without switching to another app. Click **Terminal** in the session's title bar or press **Ctrl+\`** on macOS o
The integrated terminal lets you run commands alongside your session without switching to another app. Click **Terminal** in the session's title bar or press **Ctrl+\`** on macOS o
+163 −5 lines
Upstream edited 13 Oct 2026 20:19 UTC Recorded here 13 Oct 2026 20:37 UTC
claude-code
claude-tag
±changed
+11−10
claude-codechanged
claude-tag
No line of the body moved in this read.
+11 −10 lines
Recorded here 13 Oct 2026 19:07 UTC
claude-code
desktop
±changed
+56−0
claude-codechanged
desktop
<Note>
If you use Desktop with a [third-party provider](/docs/en/third-party-integrations), SSH sessions need their own setup. See [SSH remote sessions in Claude Desktop on 3P](https://
</Note>
+56 −0 lines
Upstream edited 13 Oct 2026 19:05 UTC Recorded here 13 Oct 2026 19:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 13 Oct 2026 04:37 UTC
claude-code
agent-sdk/typescript
±changed
+2−2
claude-codechanged
agent-sdk/typescript
The following tools are available by default only on Claude 3.x models, Opus 4 through 4.7, Sonnet 4 through 4.6, and Haiku 4.5. On every other model, including model IDs Claude
The following tools are available by default only on Claude Opus 4.7, Claude Sonnet 4.6, Claude Haiku 4.5, and earlier models. On every other model, including model IDs Claude Co
The following tools are available by default only on Claude 3.x models, Opus 4 through 4.7, Sonnet 4 through 4.6, and Haiku 4.5. On every other model, including model IDs Claude
The following tools are available by default only on Claude Opus 4.7, Claude Sonnet 4.6, Claude Haiku 4.5, and earlier models. On every other model, including model IDs Claude Co
+2 −2 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
The following tools are available by default only on Claude 3.x models, Opus 4 through 4.7, Sonnet 4 through 4.6, and Haiku 4.5. On every other model, including model IDs Claude
The following tools are available by default only on Claude Opus 4.7, Claude Sonnet 4.6, Claude Haiku 4.5, and earlier models. On every other model, including model IDs Claude Co
+1 −1 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
claude-code
agent-sdk/todo-tracking
±changed
+296−300
claude-codechanged
agent-sdk/todo-tracking
<Note>
The following tools are available by default only on Claude Opus 4.7, Claude Sonnet 4.6, Claude Haiku 4.5, and earlier models. On every other model, including model IDs Claude Co
* `TodoWrite`
* `TaskCreate`
+296 −300 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
tools-reference
±changed
+2−2
claude-codechanged
tools-reference
The task-tracking tools, `TaskCreate`, `TaskGet`, `TaskUpdate`, `TaskList`, and `TodoWrite`, are available by default only on Claude 3.x models, Opus 4 through 4.7, Sonnet 4 throug
The task-tracking tools, `TaskCreate`, `TaskGet`, `TaskUpdate`, `TaskList`, and `TodoWrite`, are available by default only on Opus 4.7, Sonnet 4.6, Haiku 4.5, and earlier models. W
WebSearch is available on the Claude API, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), and Microsoft Foundry. On Google Cloud's Agent Platform it works with Claude
WebSearch is available on the Claude API, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), and Microsoft Foundry. On Google Cloud's Agent Platform it works with Opus 4,
+2 −2 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
* **Tools loaded upfront**: adding a definition invalidates the cache, and so does removing one on purpose. This applies when tool search is [below its `auto` threshold, disabled,
* **Tools loaded upfront**: adding a definition invalidates the cache, and so does removing one on purpose. This applies when tool search is [below its `auto` threshold, disabled,
+1 −1 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
* **Without tool search**: Claude uses the `WaitForMcpServers` tool instead. Configurations without tool search include a custom `ANTHROPIC_BASE_URL`, `ENABLE_TOOL_SEARCH=false`, a
* **Without tool search**: Claude uses the `WaitForMcpServers` tool instead. Configurations without tool search include a custom `ANTHROPIC_BASE_URL`, `ENABLE_TOOL_SEARCH=false`, a
+1 −1 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
claude-code
llm-gateway-protocol
±changed
+1−1
claude-codechanged
llm-gateway-protocol
| [Adaptive reasoning](/docs/en/model-config#adjust-effort-level) | No beta header. Claude Code sends `thinking: {"type": "adaptive"}` for Claude 4.6 and later, and treats model na
| [Adaptive reasoning](/docs/en/model-config#adjust-effort-level) | No beta header. Claude Code sends `thinking: {"type": "adaptive"}` for Claude Opus 4.6, Claude Sonnet 4.6, Claud
+1 −1 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
claude-code
llm-gateway-connect
±changed
+1−1
claude-codechanged
llm-gateway-connect
| `400` errors naming `thinking` or `adaptive`, such as `Input tag 'adaptive' found` | The upstream model build doesn't accept adaptive reasoning, which Claude Code requests for Cl
| `400` errors naming `thinking` or `adaptive`, such as `Input tag 'adaptive' found` | The upstream model build doesn't accept adaptive reasoning, which Claude Code requests for Cl
+1 −1 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
The list fills only in sessions that have the task-tracking tools, which Claude Code provides by default on [Claude 3.x models, Opus 4 through 4.7, Sonnet 4 through 4.6, and Haiku
The list fills only in sessions that have the task-tracking tools, which Claude Code provides by default on [Opus 4.7, Sonnet 4.6, Haiku 4.5, and earlier models](/docs/en/tools-ref
+1 −1 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
claude-code
google-vertex-ai
±changed
+1−1
claude-codechanged
google-vertex-ai
* **Earlier models, including all Claude 3.x models**: Claude Code loads MCP tool definitions upfront, because their Agent Platform serving stacks reject the required beta header.
* **Earlier models**: Claude Code loads MCP tool definitions upfront, because their Agent Platform serving stacks reject the required beta header. Setting `ENABLE_TOOL_SEARCH=true`
+1 −1 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
claude-code
feature-availability
±changed
+3−3
claude-codechanged
feature-availability
* **MCP servers**: [connectors from claude.ai](/docs/en/mcp#use-mcp-servers-from-claude-ai) load only when your claude.ai subscription is the active authentication method. [Tool se
* **MCP servers**: [connectors from claude.ai](/docs/en/mcp#use-mcp-servers-from-claude-ai) load only when your claude.ai subscription is the active authentication method. [Tool se
<span id="fn1" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>1</sup> On Google Cloud's Agent Platform, web search is available for Claude 4 models and late
<span id="fn1" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>1</sup> On Google Cloud's Agent Platform, web search is available for Opus 4, Sonnet 4, Haiku
* [Web search](/docs/en/tools-reference#websearch-tool-behavior): Claude 4 models and later
+3 −3 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
claude-code
agent-sdk/todo-tracking
±changed
+1−1
claude-codechanged
agent-sdk/todo-tracking
The following tools are available by default only on Claude 3.x models, Opus 4 through 4.7, Sonnet 4 through 4.6, and Haiku 4.5. On every other model, including model IDs Claude
The following tools are available by default only on Claude Opus 4.7, Claude Sonnet 4.6, Claude Haiku 4.5, and earlier models. On every other model, including model IDs Claude Co
+1 −1 lines
Upstream edited 13 Oct 2026 04:17 UTC Recorded here 13 Oct 2026 04:37 UTC
12 Oct 2026
1 page
+4 −4 lines
claude-code
claude-tag
±changed
+4−4
claude-codechanged
claude-tag
No line of the body moved in this read.
+4 −4 lines
Recorded here 12 Oct 2026 23:07 UTC
11 Oct 2026
20 pages
+334 −160 lines
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 11 Oct 2026 23:07 UTC
claude-code
agent-sdk/typescript
±changed
+26−4
claude-codechanged
agent-sdk/typescript
runId?: string;
A background task can run more than once under the same `task_id`, such as when Claude [resumes a subagent](/docs/en/agent-sdk/subagents#resume-subagents). Each run has its own [`r
Notification when a background task completes, fails, or is stopped. Background tasks include `run_in_background` Bash commands, [Monitor](#monitor) watches, and background subagen
Notification when a background task completes, fails, or is stopped. Background tasks include `run_in_background` Bash commands, [Monitor](#monitor) watches, and background subagen
+26 −4 lines
Upstream edited 11 Oct 2026 22:40 UTC Recorded here 11 Oct 2026 23:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 11 Oct 2026 22:37 UTC
claude-code
authentication
±changed
+65−73
claude-codechanged
authentication
<Steps>
<Step title="Subscribe">
Subscribe to [Claude for Teams](https://claude.com/pricing?utm_source=claude_code\&utm_medium=docs\&utm_content=authentication_teams_step#team-&-enterprise) or contact sales fo
</Step>
+65 −73 lines
Upstream edited 11 Oct 2026 22:34 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
errors
±changed
+19−14
claude-codechanged
errors
| `Login expired · Run /login to sign in again, or re-authenticate your Anthropic profile` | [Authentication](#anthropic-profile-login-expired) |
For a `Login expired` message that ends with `or re-authenticate your Anthropic profile`, see [Anthropic profile login expired](#anthropic-profile-login-expired).
Claude Code is authenticating through an Anthropic credential profile whose saved login credential has expired, and the profile holds no refresh credential Claude Code can use to r
Claude Code is authenticating through an Anthropic credential profile whose saved login credential has expired, and the profile holds no refresh credential Claude Code can use to r
+19 −14 lines
Upstream edited 11 Oct 2026 22:34 UTC Recorded here 11 Oct 2026 22:37 UTC
claude-code
authentication
±changed
+2−2
claude-codechanged
authentication
In practice, the profile stores an OAuth login while an API key is a static credential: Claude Code refreshes the profile's login automatically, and when refresh fails, requests fa
In practice, the profile stores an OAuth login while an API key is a static credential. Claude Code refreshes the profile's login automatically, and when refresh fails, requests fa
When a `user_oauth` profile's login has expired and Claude Code can't renew it, requests fail with [Anthropic profile login expired](/docs/en/errors#anthropic-profile-login-expired
When a `user_oauth` profile's login has expired and Claude Code can't renew it, requests fail with an [expired profile login error](/docs/en/errors#anthropic-profile-login-expired)
+2 −2 lines
Upstream edited 11 Oct 2026 22:34 UTC Recorded here 11 Oct 2026 22:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 11 Oct 2026 20:07 UTC
claude-code
plugins/mods/reference
±changed
+1−0
claude-codechanged
plugins/mods/reference
| `prompt.autocomplete` | The user types in the prompt box and a word ends at the cursor. `e.token` is that word. Claude Code doesn't wait for the hook: its own autocomplete rows s
+1 −0 lines
Upstream edited 11 Oct 2026 19:45 UTC Recorded here 11 Oct 2026 20:07 UTC
claude-code
scheduled-tasks
±changed
+15−10
claude-codechanged
scheduled-tasks
A scheduled task can run at a different time than its schedule says. If every session's tasks ran exactly on schedule, many of them would call the API at the same moment, so Claude
A scheduled task can run at a different time than its schedule says. If every session's tasks ran exactly on schedule, many of them would call the API at the same moment, so Claude
When you create a recurring task, Claude Code gives it a fixed delay and adds that delay to every run. The delay is worked out from the task's ID, so the same task runs the same nu
Tasks that run more often get shorter delays, and 30 minutes is the longest delay a task can get. These are the delay ranges for some common schedules:
+15 −10 lines
Upstream edited 11 Oct 2026 19:43 UTC Recorded here 11 Oct 2026 20:07 UTC
claude-code
settings-reference
±changed
+2−2
claude-codechanged
settings-reference
* `true`: Claude Code runs sandboxed Bash commands without a permission prompt, subject to `deny` rules and content-scoped `ask` rules; `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB` turns a
* `true`: Claude Code runs sandboxed Bash commands without a permission prompt, except in the cases that [Auto-allow mode](/docs/en/sandboxing#auto-allow-mode) describes; `CLAUDE
See [Sandbox modes](/docs/en/sandboxing#sandbox-modes) for what auto-allow mode still prompts on and how it behaves in plan mode.
See [Auto-allow mode](/docs/en/sandboxing#auto-allow-mode) for what auto-allow mode still prompts on and how it behaves in plan mode.
+2 −2 lines
Upstream edited 11 Oct 2026 19:38 UTC Recorded here 11 Oct 2026 20:07 UTC
claude-code
sandboxing
±changed
+11−1
claude-codechanged
sandboxing
* A bare `Bash` ask rule, or the equivalent `Bash(*)` form, is skipped for commands that run sandboxed; it still applies to commands that fall back to the regular permission flow.
* A bare `Bash` ask rule, or the equivalent `Bash(*)` form, is skipped for commands that run sandboxed; it still applies to commands that run outside the sandbox. In [plan mode](/d
Some sandboxed commands also go through the regular [permission flow](/docs/en/permissions) instead of being approved automatically. This happens with commands such as `FOO=bar npm
+11 −1 lines
Upstream edited 11 Oct 2026 19:38 UTC Recorded here 11 Oct 2026 20:07 UTC
claude-code
permissions
±changed
+1−0
claude-codechanged
permissions
* Other sandboxed commands can go through the regular permission flow too, as [Auto-allow mode](/docs/en/sandboxing#auto-allow-mode) describes
+1 −0 lines
Upstream edited 11 Oct 2026 19:38 UTC Recorded here 11 Oct 2026 20:07 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
| Iterate locally with fewer prompts, without a classifier | Manual mode plus the Bash sandbox in [auto-allow mode](/docs/en/sandboxing#sandbox-modes): `claude --permission-mode de
| Iterate locally with fewer prompts, without a classifier | Manual mode plus the Bash sandbox in [auto-allow mode](/docs/en/sandboxing#sandbox-modes): `claude --permission-mode de
+1 −1 lines
Upstream edited 11 Oct 2026 19:38 UTC Recorded here 11 Oct 2026 20:07 UTC
claude-code
worktrees
±changed
+1−1
claude-codechanged
worktrees
Each subagent gets a temporary worktree that Claude Code removes automatically when the subagent finishes without changes; a worktree with changes stays on disk until the [periodic
Each subagent gets a temporary worktree that Claude Code removes automatically when the subagent finishes without changes; a worktree with changes stays on disk until the [periodic
+1 −1 lines
Upstream edited 11 Oct 2026 19:37 UTC Recorded here 11 Oct 2026 20:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.