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
757 changed this week · last read 22 Oct 2026
Claude Code CLI
228pages tracked
151 changed this week · last read 22 Oct 2026
Claude Documentation
279pages tracked
76 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
5,527 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
9 Oct 2026
65 pages
+3225 −2197 lines
claude-code
monitoring-usage
±changed
+6−4
claude-codechanged
monitoring-usage
* `attempt`: Total number of attempts made, including the initial request (`1` means no retries occurred)
* `attempt`: Number of attempts made, including the initial request. [Detect retry exhaustion](#detect-retry-exhaustion) says when the count starts again
The `attempt` attribute on the event records the total number of attempts. `CLAUDE_CODE_MAX_RETRIES` defaults to 10 and is capped at 15. On v2.1.199 or later, you can set `CLAUDE_C
When the request exhausts all retries on a transient error, `attempt` equals one more than that effective limit: 11 by default, and never more than 16 unless the watchdog is set. A
+6 −4 lines
Upstream edited 9 Oct 2026 14:19 UTC Recorded here 9 Oct 2026 14:37 UTC
claude-code
agent-sdk/typescript
±changed
+3−1
claude-codechanged
agent-sdk/typescript
* `CLAUDE_CODE_MAX_RETRIES`: maximum API retries. Default `10`, capped at `15`. Each retry gets its own `API_TIMEOUT_MS` window, so worst-case wall time is roughly `API_TIMEOUT_MS
* `CLAUDE_CODE_MAX_RETRIES`: maximum API retries. Default `10`, capped at `15`. Each retry gets its own `API_TIMEOUT_MS` window.
For unattended runs that need to wait through longer outages, set [`CLAUDE_CODE_RETRY_WATCHDOG=1`](/docs/en/errors#tune-retry-behavior): it retries transient capacity errors inde
+3 −1 lines
Upstream edited 9 Oct 2026 14:19 UTC Recorded here 9 Oct 2026 14:37 UTC
claude-code
agent-sdk/python
±changed
+3−1
claude-codechanged
agent-sdk/python
* `CLAUDE_CODE_MAX_RETRIES`: maximum API retries. Default `10`, capped at `15`. Each retry gets its own `API_TIMEOUT_MS` window, so worst-case wall time is roughly `API_TIMEOUT_MS
* `CLAUDE_CODE_MAX_RETRIES`: maximum API retries. Default `10`, capped at `15`. Each retry gets its own `API_TIMEOUT_MS` window.
For unattended runs that need to wait through longer outages, set [`CLAUDE_CODE_RETRY_WATCHDOG=1`](/docs/en/errors#tune-retry-behavior): it retries transient capacity errors inde
+3 −1 lines
Upstream edited 9 Oct 2026 14:19 UTC Recorded here 9 Oct 2026 14:37 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 9 Oct 2026 03:37 UTC
claude-code
agent-sdk/user-input
±changed
+12−12
claude-codechanged
agent-sdk/user-input
1. **Tool needs approval**: Claude wants to use a tool that isn't auto-approved by a [permission rule](/docs/en/agent-sdk/permissions) or permission mode. Check `tool_name` for the
1. **Tool needs approval**: Claude wants to use a tool that isn't auto-approved by a [permission rule](/docs/en/agent-sdk/permissions.md) or permission mode. Check `tool_name` for
> **The callback never fires for auto-approved tools.** Any approval earlier in the [permission evaluation flow](/docs/en/agent-sdk/permissions#how-permissions-are-evaluated), an a
> **The callback never fires for auto-approved tools.** Any approval earlier in the [permission evaluation flow](/docs/en/agent-sdk/permissions.md#how-permissions-are-evaluated), a
> An allow rule doesn't pre-approve the [actions no mode auto-approves](/docs/en/permission-modes#actions-no-mode-auto-approves); see [How permissions are evaluated](/docs/en/agent
+12 −12 lines
Upstream edited 9 Oct 2026 03:28 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
agent-sdk/user-input
±changed
+576−602
claude-codechanged
agent-sdk/user-input
<CodeGroup>
```python Python theme={null}
from claude_agent_sdk import ClaudeAgentOptions
+576 −602 lines
Upstream edited 9 Oct 2026 03:28 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/user-input
±changed
+10−5
claude-codechanged
agent-sdk/user-input
async function handleToolRequest(toolName, input, options) {
import type { CanUseTool } from "@anthropic-ai/claude-agent-sdk";
const handleToolRequest: CanUseTool = async (toolName, input, options) => {
// Prompt user and return allow or deny
+10 −5 lines
Upstream edited 9 Oct 2026 03:28 UTC Recorded here 9 Oct 2026 03:37 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 9 Oct 2026 01:37 UTC
claude-code
ultrareview
±changed
+7−7
claude-codechanged
ultrareview
To review a GitHub pull request instead of a local branch, pass the PR number:
To review a pull request on `github.com` instead of a local branch, pass the PR number:
In PR mode, the cloud sandbox clones the pull request directly from the host rather than bundling your local working tree. PR mode works with repositories on `github.com` and on [G
For repositories on `github.com`, the sandbox clones with the GitHub account connected to your Claude account, so the account must be able to read the PR's repository.
+7 −7 lines
Upstream edited 9 Oct 2026 01:16 UTC Recorded here 9 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 9 Oct 2026 01:07 UTC
claude-code
workflows
±changed
+25−1
claude-codechanged
workflows
An `agent()` call resolves to `null` if you stop it mid-run or it hits an unrecoverable API error. `pipeline()` keeps each `null` in the results array, which is why the example end
An `agent()` call resolves to `null` if you stop it mid-run or it hits an unrecoverable API error. `pipeline()` keeps each `null` in the results array, which is why the example end
### When an agent stalls and restarts
An agent whose output stops arriving for long enough starts over from the same prompt. In [`/workflows`](#watch-the-run), its name gains a `(retry 1)` suffix and its detail shows `
+25 −1 lines
Upstream edited 9 Oct 2026 00:59 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
* Large pages are truncated to a fixed character limit before processing.
* WebFetch reads up to 100,000 characters of a page's content per call. On Claude Code v2.1.290 or later, the result for a longer page tells Claude how much went unread, so Claude
+1 −1 lines
Upstream edited 9 Oct 2026 00:55 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
hooks
±changed
+1−0
claude-codechanged
hooks
| `offset` | number | `100000` | Optional number of characters to skip from the start of the page. Claude sets it to keep reading a long page. Requires Claude Code v2.1.290 or late
+1 −0 lines
Upstream edited 9 Oct 2026 00:55 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
agent-sdk/typescript
±changed
+4−1
claude-codechanged
agent-sdk/typescript
| `maxBudgetUsd` | `number` | `undefined` | Stop the query when the client-side cost estimate reaches this USD value. Counts only the call's own spend; totals restored from a resum
| `maxBudgetUsd` | `number` | `undefined` | Stop the query when the client-side cost estimate reaches this USD value. The estimate can pass this value, so [leave headroom](/docs/en
offset?: number;
`offset` is the number of characters to skip from the start of the page. Claude sets it to keep reading a long page. The field requires Agent SDK v0.3.290 or later.
+4 −1 lines
Upstream edited 9 Oct 2026 00:55 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
agent-sdk/python
±changed
+2−1
claude-codechanged
agent-sdk/python
| `max_budget_usd` | `float \| None` | `None` | Stop the query when the client-side cost estimate reaches this USD value. Counts only the call's own spend; totals restored from a r
| `max_budget_usd` | `float \| None` | `None` | Stop the query when the client-side cost estimate reaches this USD value. The estimate can pass this value, so [leave headroom](/doc
"offset": int | None, # Number of characters to skip from the start of the page. Requires Python Agent SDK 0.2.164 or later
+2 −1 lines
Upstream edited 9 Oct 2026 00:55 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
skills
±changed
+2−0
claude-codechanged
skills
| `managed-agents-onboard <url>` | Build the Managed Agent that the page at the URL describes, such as a page in the [Managed Agents docs](https://platform.claude.com/docs/en/manag
| `managed-agents-onboard <quickstart-name>` | Build one of the Console's quickstart templates, such as `deep-researcher`. If you give one word that isn't a template name, Claude l
+2 −0 lines
Upstream edited 9 Oct 2026 00:54 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
server-managed-settings
±changed
+4−0
claude-codechanged
server-managed-settings
The editor checks your JSON against the published JSON schema for Claude Code settings. If it finds a problem in JSON that parses, it shows a warning and relabels the save butt
The schema [can lag behind the newest releases](/docs/en/settings#edit-a-settings-file), so the editor can flag a key or value that the [settings reference](/docs/en/settings-r
+4 −0 lines
Upstream edited 9 Oct 2026 00:52 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
agent-sdk/agent-loop
±changed
+5−1
claude-codechanged
agent-sdk/agent-loop
| Max budget (`max_budget_usd` / `maxBudgetUsd`) | Maximum cost before stopping | No limit |
| Max budget (`max_budget_usd` / `maxBudgetUsd`) | Estimated spend at which the loop stops | No limit |
#### Budget headroom
+5 −1 lines
Upstream edited 9 Oct 2026 00:50 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
monitoring-usage
±changed
+4−0
claude-codechanged
monitoring-usage
<Note>
Events that Claude Code logs before a developer signs in don't carry the gateway identity. When Claude Code opens a session signed out of the gateway, for example after [the gate
</Note>
+4 −0 lines
Upstream edited 9 Oct 2026 00:48 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
claude-apps-gateway-on-aws
±changed
+1−1
claude-codechanged
claude-apps-gateway-on-aws
The gateway gives you per-developer usage metrics without any per-machine OTEL configuration. Claude Code emits OpenTelemetry (OTLP) metrics, logs, and opt-in traces; [Monitoring u
The gateway gives you per-developer usage metrics without any per-machine OTEL configuration. Claude Code emits OpenTelemetry (OTLP) metrics, logs, and opt-in traces; [Monitoring u
+1 −1 lines
Upstream edited 9 Oct 2026 00:48 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
claude-apps-gateway-config
±changed
+1−1
claude-codechanged
claude-apps-gateway-config
In sessions signed in through `/login`, the CLI stamps each export with the authenticated user's identity, read from the gateway-issued JWT: the `user.id`, `user.email`, and `user.
In sessions signed in through `/login`, the CLI stamps each export with the authenticated user's identity, read from the gateway-issued JWT: the `user.id`, `user.email`, and `user.
+1 −1 lines
Upstream edited 9 Oct 2026 00:48 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
plugins/mods/troubleshoot
±changed
+13−1
claude-codechanged
plugins/mods/troubleshoot
The mod loaded, and its pane, band, or controls don't behave as you expect.
The mod loaded, and its pane, band, toast, or controls don't behave as you expect.
### A toast doesn't appear
+13 −1 lines
Upstream edited 9 Oct 2026 00:45 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
plugins/mods/interface
±changed
+10−4
claude-codechanged
plugins/mods/interface
<img src="https://mintcdn.com/claude-code/dgiVO_Od1X1faduV/images/mods-screen-map.svg?fit=max&auto=format&n=dgiVO_Od1X1faduV&q=85&s=5fda26b6609c62b68c6f9e528c1590ea" className="dar
<img src="https://mintcdn.com/claude-code/dgiVO_Od1X1faduV/images/mods-screen-map-dark.svg?fit=max&auto=format&n=dgiVO_Od1X1faduV&q=85&s=5b4161581a1bd2c0450b0c8b57bc1225" className
<img src="https://mintcdn.com/claude-code/dgiVO_Od1X1faduV/images/mods-screen-map.svg?fit=max&auto=format&n=dgiVO_Od1X1faduV&q=85&s=5fda26b6609c62b68c6f9e528c1590ea" className="dar
+10 −4 lines
Upstream edited 9 Oct 2026 00:45 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
plugins/mods/api
±changed
+1−1
claude-codechanged
plugins/mods/api
| `$.ui.toast(text)` | A toast notification at the top right, with the mod's name above the text, that disappears after a few seconds |
| `$.ui.toast(text)` | A toast notification with the mod's name that disappears after a few seconds. It's a box at the top right in [fullscreen rendering](/docs/en/fullscreen), and
+1 −1 lines
Upstream edited 9 Oct 2026 00:45 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
worktrees
±changed
+1−1
claude-codechanged
worktrees
These checks read the path an edit targets, the directory a command runs in, and the text of the command. None of them tracks which files a shell command writes, so a command that
These checks read the path an edit targets, the directory a command runs in, and the text of the command. None of them tracks which files a shell command writes, so a command that
+1 −1 lines
Upstream edited 9 Oct 2026 00:42 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
An isolation mode that runs Claude in a separate git worktree under `.claude/worktrees/`, enabled with the `-w` flag or `isolation: worktree` in subagent config. Changes stay on a
An isolation mode that runs Claude in a separate git worktree under `.claude/worktrees/`, enabled with the `-w` flag or `isolation: worktree` in subagent config. Changes stay on a
+1 −1 lines
Upstream edited 9 Oct 2026 00:42 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
desktop
±changed
+1−1
claude-codechanged
desktop
Click **+ New session** in the sidebar, or press **Cmd+N** on macOS or **Ctrl+N** on Windows, to work on multiple tasks in parallel. Press **Ctrl+Tab** and **Ctrl+Shift+Tab** to cy
Click **+ New session** in the sidebar, or press **Cmd+N** on macOS or **Ctrl+N** on Windows, to work on multiple tasks in parallel. Press **Ctrl+Tab** and **Ctrl+Shift+Tab** to cy
+1 −1 lines
Upstream edited 9 Oct 2026 00:42 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
claude-projects
±changed
+1−1
claude-codechanged
claude-projects
* **Worktrees**: a [worktree](/docs/en/worktrees) gives each local session its own working copy of a repository so parallel sessions on your machine don't overwrite each other. Clo
* **Worktrees**: a [worktree](/docs/en/worktrees) gives each local session its own working copy of a repository. Cloud threads don't need them: each clones its repositories into it
+1 −1 lines
Upstream edited 9 Oct 2026 00:42 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
agent-view
±changed
+1−1
claude-codechanged
agent-view
When the hook fails in a directory that isn't a git repository, Claude skips isolation for that directory and edits the working directory in place. Inside a git repository, a sessi
When the hook fails in a directory that isn't a git repository, Claude skips isolation for that directory and edits the working directory in place. Inside a git repository, a sessi
+1 −1 lines
Upstream edited 9 Oct 2026 00:42 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
self-hosted-environments-configuration
±changed
+14−3
claude-codechanged
self-hosted-environments-configuration
* `<repo>/.mcp.json`: project scope. Commit the file to the repository; its servers are auto-approved in cloud sessions.
* `<repo>/.mcp.json`: project scope. Commit the file to the repository; its servers are auto-approved in cloud sessions. In a session with several repositories, [at most one reposi
The hook prompts Claude to commit and push before the session ends, and stays silent when the directory isn't a git repository or has no remote.
The hook prompts Claude to commit and push before the session ends, and stays silent when the directory isn't a git repository or has no remote. For a session with several reposito
Repository-committed `.claude/settings.json` layers on top as project settings. Sessions also read [`managed-settings.json`](/docs/en/settings#where-settings-live) from the standar
+14 −3 lines
Upstream edited 9 Oct 2026 00:39 UTC Recorded here 9 Oct 2026 01:07 UTC
claude-code
cloud-environments
±changed
+3−3
claude-codechanged
cloud-environments
| Your repo's `.claude/settings.json` hooks and permission rules | Yes, in a session with one repository | Part of the clone. A session with several repositories, including a [proj
| Your repo's `.mcp.json` MCP servers | Yes, in a session with one repository | Part of the clone, found from the session's working directory |
| Your repo's `.claude/settings.json` hooks and permission rules | Yes, in a session with one repository | Part of the clone. For a session with several repositories, see [which se
| Your repo's `.mcp.json` MCP servers | Yes, in a session with one repository | Part of the clone, found from the session's working directory. For a self-hosted environment, see [w
* **One repository per session**: a session with several repositories doesn't load hooks from any repository's `.claude/settings.json`, so a SessionStart hook you define there does
+3 −3 lines
Upstream edited 9 Oct 2026 00:39 UTC Recorded here 9 Oct 2026 01:07 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 9 Oct 2026 00:37 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
* Each execution creates a separate background process. There is no deduplication across multiple firings of the same async hook.
* Each execution creates a separate background process.
+1 −1 lines
Upstream edited 9 Oct 2026 00:30 UTC Recorded here 9 Oct 2026 00:37 UTC
8 Oct 2026
71 pages
+8066 −5601 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 8 Oct 2026 23:07 UTC
claude-code
sub-agents
±changed
+3−1
claude-codechanged
sub-agents
* When the main conversation is in `default`, `dontAsk`, or `plan` mode, the subagent runs in the permission mode you set, except `bypassPermissions`. A subagent that declares `byp
* When the main conversation is in `default`, `dontAsk`, or `plan` mode, the subagent runs in the permission mode you set. It keeps the main conversation's permission mode instead
* You set `bypassPermissions`. The `bypassPermissions` exception requires Claude Code v2.1.267 or later.
* You set `auto` and [auto mode isn't available](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) to the subagent, such as when a settings file sets [`disableAutoMode`
+3 −1 lines
Upstream edited 8 Oct 2026 23:03 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
plugins/mods/events
±changed
+2−0
claude-codechanged
plugins/mods/events
To see the tool calls that the API ran itself during the request, such as calls to the [advisor tool](/docs/en/advisor), read `result.serverToolUses`. Claude Code doesn't run these
+2 −0 lines
Upstream edited 8 Oct 2026 23:03 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
agent-sdk/permissions
±changed
+1−1
claude-codechanged
agent-sdk/permissions
**Subagent inheritance:** A subagent runs in the parent session's permission mode unless you set `permissionMode` on its [`AgentDefinition`](/docs/en/agent-sdk/typescript#agentde
**Subagent inheritance:** A subagent runs in the parent session's permission mode unless you set `permissionMode` on its [`AgentDefinition`](/docs/en/agent-sdk/typescript#agentde
+1 −1 lines
Upstream edited 8 Oct 2026 23:03 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
plugins/mods/reference
±changed
+2−1
claude-codechanged
plugins/mods/reference
| `$.agent` | `register`, `spawn`, `list` |
| `$.agent` | `register`, `spawn`, `list`. `list()` returns this session's subagents and teammates, each with a `status` of `pending`, `running`, `waiting`, `idle`, `completed`, `f
| A hook's `drop` reason or `config.set` `deny` reason | 4,096 characters. The end of a longer reason is cut, and the drop or deny still applies. The cut requires Claude Code v2.1.
+2 −1 lines
Upstream edited 8 Oct 2026 23:01 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
plugins/mods/api
±changed
+9−1
claude-codechanged
plugins/mods/api
A mod can send a plain-text message to another of your sessions or to one of this session's subagents, and observe the messages that arrive and leave. `$.session.send({ to, text })
A mod can send a plain-text message to another of your sessions, to one of this session's subagents, or to a teammate in its [agent team](/docs/en/agent-teams). It can also observe
To send one, call `$.session.send({ to, text })`, which makes the same delivery the SendMessage tool makes. Set `to` by who receives the message:
+9 −1 lines
Upstream edited 8 Oct 2026 23:01 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
plugins/mods/admin
±changed
+1−1
claude-codechanged
plugins/mods/admin
| `$.session.send` | Sends a message that another session's or subagent's Claude reads |
| `$.session.send` | Sends a message that another session's, subagent's, or [teammate's](/docs/en/agent-teams) Claude reads |
+1 −1 lines
Upstream edited 8 Oct 2026 23:01 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
agent-sdk/typescript
±changed
+23−3
claude-codechanged
agent-sdk/typescript
agent_id?: string;
`agent_id` identifies the subagent that produced the message and is absent on main-thread messages. The value equals the `task_id` on that subagent's [`task_started`](#sdktaskstart
Match a subagent's messages to its task events on `agent_id` rather than pairing a message's `parent_tool_use_id` with a task event's `tool_use_id`. When a tool call resumes the su
+23 −3 lines
Upstream edited 8 Oct 2026 22:59 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
agent-sdk/subagents
±changed
+9−2
claude-codechanged
agent-sdk/subagents
Claude invokes subagents through the Agent tool. To detect when a subagent is invoked, check for `tool_use` blocks where `name` is `"Agent"`. Messages from within a subagent's cont
Claude invokes subagents through the Agent tool. To detect when a subagent is invoked, check for `tool_use` blocks where `name` is `"Agent"`.
Messages from within a subagent's context include a `parent_tool_use_id` field. In TypeScript, each assistant and user message a subagent produces also carries [`agent_id`](/docs/e
This example iterates through streamed messages, logging when a subagent is invoked and when subsequent messages originate from within that subagent's execution context.
+9 −2 lines
Upstream edited 8 Oct 2026 22:59 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
plugins/mods/test
±changed
+2−6
claude-codechanged
plugins/mods/test
<h3 id="test-a-drawing-after-clear">
Test a drawing after `/clear`
</h3>
### Test a drawing after `/clear`
<h2 id="test-a-mod-that-judges-other-mods">
+2 −6 lines
Upstream edited 8 Oct 2026 22:59 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
plugins/mods/test
±changed
+7−2
claude-codechanged
plugins/mods/test
The kit also exports in-memory mocks that answer a whole namespace for you. `mock.clock(on)` answers [`$.clock`](/docs/en/plugins/mods/api#run-work-in-the-background), `mock.store(
The kit also exports ready-made mocks for the clock, the store, environment variables, and rows appended to the conversation:
* **`mock.clock(on)`**: answers [`$.clock`](/docs/en/plugins/mods/api#run-work-in-the-background) and returns a mock clock that your test advances, so a test of a timer doesn't wai
* **`mock.store(on, { count: 7 })`**: answers `$.store` from a store that starts with those entries. It returns nothing, so to check what your mod saved, write the two `store` stub
+7 −2 lines
Upstream edited 8 Oct 2026 22:59 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
hooks
±changed
+16−8
claude-codechanged
hooks
Claude Code adds stdout it [treats as plain text](#exit-code-0) to Claude's context. In addition to the [JSON output fields](#json-output) available to all hooks, you can return th
A SessionStart hook can add context for Claude, supply the first user message, set the session title, watch files, and reload skills. Return the field for each one, in addition to
| `initialUserMessage` | String used as the first user message of the session. Applies in [non-interactive mode](/docs/en/headless) with the `-p` flag, where it becomes the first t
| `sessionTitle` | Sets the session title, with the same effect as `/rename`. Use to name sessions automatically from the launch folder, git branch, or worktree name. Applies when
| `initialUserMessage` | String used as the first user message of the session, in [non-interactive mode](/docs/en/headless) with the `-p` flag. It becomes the first turn even if yo
+16 −8 lines
Upstream edited 8 Oct 2026 22:59 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
plugins/troubleshooting
±changed
+2−2
claude-codechanged
plugins/troubleshooting
You ran `/plugin marketplace add <source>` or `claude plugin marketplace add <source>`, and Claude Code replied `Invalid marketplace source format. Try: owner/repo, https://..., or
You ran `/plugin marketplace add <source>`, `claude plugin marketplace add <source>`, or `claude plugin install <plugin> --marketplace <source>`, and Claude Code replied `Invalid m
You confirmed adding a marketplace through [`/plugin install <plugin> --marketplace <source>`](/docs/en/plugins/install#add-a-marketplace-and-install-in-one-command), and the catal
You named a new marketplace source with [`--marketplace <source>` on the install command](/docs/en/plugins/install#add-a-marketplace-and-install-in-one-command), in a session or fr
+2 −2 lines
Upstream edited 8 Oct 2026 22:56 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
plugins/publish
±changed
+1−0
claude-codechanged
plugins/publish
* Or do both from the shell in one command: `claude plugin install deploy-helper --marketplace your-org/your-marketplace`. Requires Claude Code v2.1.292 or later
+1 −0 lines
Upstream edited 8 Oct 2026 22:56 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
plugins/install
±changed
+16−4
claude-codechanged
plugins/install
* **The marketplace must be added first**: on a machine where no one has opened an interactive Claude Code session yet, the official marketplace isn't registered, so a script that
* **The marketplace on a new machine**: on a machine where no one has opened an interactive Claude Code session yet, the official marketplace isn't registered, so a script that ins
To install a plugin from a marketplace you haven't added yet, run `/plugin install` in a Claude Code session and name the marketplace source with `--marketplace`. Requires Claude C
To install a plugin from a marketplace you haven't added yet, name the marketplace source with `--marketplace` on the install command, in a session or from your shell. The source t
+16 −4 lines
Upstream edited 8 Oct 2026 22:56 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
plugins/cli-reference
±changed
+1−0
claude-codechanged
plugins/cli-reference
| `--marketplace <source>` | Install `<plugin>`, given by its bare name, from the marketplace at `<source>`, adding the marketplace first if you haven't added it yet. See [Add a ma
+1 −0 lines
Upstream edited 8 Oct 2026 22:56 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
You confirmed adding a marketplace through [`/plugin install <plugin> --marketplace <source>`](/docs/en/plugins/install#add-a-marketplace-and-install-in-one-command), and the catal
You named a new marketplace source with [`--marketplace <source>` on the install command](/docs/en/plugins/install#add-a-marketplace-and-install-in-one-command), in a session or fr
+1 −1 lines
Upstream edited 8 Oct 2026 22:56 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
artifacts
±changed
+42−16
claude-codechanged
artifacts
Unless you name a location, Claude writes the page to an HTML or Markdown file in a temporary directory outside your project, then publishes it. Outside [plan mode](/docs/en/permis
The artifact stays private to you until you [share it](#share-an-artifact). After you share it publicly, Claude Code asks for your approval once per conversation before changing it
If you turned [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) off, Claude Code asks before the first publish of each artifact, or in auto mode h
+42 −16 lines
Upstream edited 8 Oct 2026 22:44 UTC Recorded here 8 Oct 2026 23:07 UTC
claude-code
vs-code
±changed
+1−1
claude-codechanged
vs-code
| `showMessageTimestamps` | `false` | Show when each message was sent. A date line marks where the day changes. Requires Claude Code v2.1.284 or later |
| `showMessageTimestamps` | `true` | Show when each message was sent. A date line marks where the day changes. Requires Claude Code v2.1.284 or later. Before v2.1.290, the default
+1 −1 lines
Upstream edited 8 Oct 2026 22:38 UTC Recorded here 8 Oct 2026 23:07 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 8 Oct 2026 22:07 UTC
claude-code
sub-agents
±changed
+8−2
claude-codechanged
sub-agents
| `effort` | No | Effort level when this subagent is active. Overrides the session effort level, but not the [`CLAUDE_CODE_EFFORT_LEVEL`](/docs/en/env-vars#variables) environment v
| `effort` | No | Effort level when this subagent is active. Overrides the session effort level, but not the [`CLAUDE_CODE_EFFORT_LEVEL`](/docs/en/env-vars#variables) environment v
To check which model a subagent is running on, run [`/tasks`](/docs/en/commands). Claude Code names the model on the subagent's row, and adds the [effort level](/docs/en/model-conf
To check which model a subagent is running on, run [`/tasks`](/docs/en/commands). Claude Code names the model on the subagent's row, and adds the [effort level](/docs/en/model-conf
+8 −2 lines
Upstream edited 8 Oct 2026 21:58 UTC Recorded here 8 Oct 2026 22:07 UTC
claude-code
agent-sdk/typescript
±changed
+1−0
claude-codechanged
agent-sdk/typescript
effort?: "low" | "medium" | "high" | "xhigh" | "max";
+1 −0 lines
Upstream edited 8 Oct 2026 21:58 UTC Recorded here 8 Oct 2026 22:07 UTC
claude-code
plugins/mods/reference
±changed
+9−0
claude-codechanged
plugins/mods/reference
#### Agent and organization fields on `tool.check`
In a `tool.check` hook, read these fields to tell a subagent's call from the main conversation's, and to see whether your organization requires approval for a connector tool:
+9 −0 lines
Upstream edited 8 Oct 2026 21:57 UTC Recorded here 8 Oct 2026 22:07 UTC
claude-code
settings-reference
±changed
+4−2
claude-codechanged
settings-reference
Before v2.1.251, project and local settings could also set the variables in this list that choose where Claude Code writes its files or that export session content, except `HOME`
* Variables that set the timers on an unanswered dialog: [`CLAUDE_CODE_USER_DIALOG_TIMEOUT_MS`, `CLAUDE_AFK_TIMEOUT_MS`, and `CLAUDE_AFK_COUNTDOWN_MS`](/docs/en/env-vars#variable
* [`CLAUDE_CODE_DISABLE_ATTACHMENTS`](/docs/en/env-vars#variables), which turns off attachment processing.
+4 −2 lines
Upstream edited 8 Oct 2026 21:45 UTC Recorded here 8 Oct 2026 22:07 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 8 Oct 2026 21:07 UTC
claude-code
errors
±changed
+1−0
claude-codechanged
errors
| [`CLAUDE_CODE_OVERLOADED_RETRY_BASE_DELAY_MS`](/docs/en/env-vars) | 500 | Starting delay in milliseconds of the backoff between retries of a request that the API rejects with a `
+1 −0 lines
Upstream edited 8 Oct 2026 20:58 UTC Recorded here 8 Oct 2026 21:07 UTC
claude-code
plugins/mods/reference
±changed
+2−1
claude-codechanged
plugins/mods/reference
| `Link` | `href`, `label` | ✓ | ✓ |
| [`Link`](/docs/en/plugins/mods/interface#link-in-the-desktop-app) | `href`, `label`. See [Limits](#limits). | ✓ | ✓ |
| A `Link`'s `href` | 2,048 characters. A longer `href` keeps the whole tree from drawing. |
+2 −1 lines
Upstream edited 8 Oct 2026 20:57 UTC Recorded here 8 Oct 2026 21:07 UTC
claude-code
plugins/mods/interface
±changed
+12−0
claude-codechanged
plugins/mods/interface
<h3 id="link-in-the-desktop-app">
`Link` in the Desktop app
</h3>
+12 −0 lines
Upstream edited 8 Oct 2026 20:57 UTC Recorded here 8 Oct 2026 21:07 UTC
claude-code
hooks
±changed
+3−0
claude-codechanged
hooks
| `agent_id` | On this event, the [common input field](#common-input-fields) identifies the subagent or [in-process teammate](/docs/en/agent-teams#choose-a-display-mode) creating t
| `agent_id` | On this event, the [common input field](#common-input-fields) identifies the subagent or [in-process teammate](/docs/en/agent-teams#choose-a-display-mode) completing
| `agent_id` | On this event, the [common input field](#common-input-fields) identifies the [in-process teammate](/docs/en/agent-teams#choose-a-display-mode) that is about to go id
+3 −0 lines
Upstream edited 8 Oct 2026 20:57 UTC Recorded here 8 Oct 2026 21:07 UTC
claude-code
plugins/mods/troubleshoot
±changed
+8−0
claude-codechanged
plugins/mods/troubleshoot
### A `ui.render` line says `threw while drawn`
The line names the [render site](/docs/en/plugins/mods/reference#render-sites), then says `threw while drawn:` and the error, as in `first-mod: ui.render (ToolUse) threw while draw
Read the error and fix the value in your hook that caused it.
+8 −0 lines
Upstream edited 8 Oct 2026 20:48 UTC Recorded here 8 Oct 2026 21:07 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 8 Oct 2026 20:37 UTC
claude-code
mcp
±changed
+32−3
claude-codechanged
mcp
[Plugins](/docs/en/plugins/overview) can bundle MCP servers that provide tools and integrations when you enable the plugin. Plugin MCP servers work identically to user-configured s
[Plugins](/docs/en/plugins/overview) can bundle MCP servers that provide tools and integrations when you enable the plugin.
<h4 id="per-tool-alwaysload">
Mark a tool to load upfront or stay deferred
</h4>
+32 −3 lines
Upstream edited 8 Oct 2026 20:28 UTC Recorded here 8 Oct 2026 20:37 UTC
claude-code
agent-sdk/typescript
±changed
+7−1
claude-codechanged
agent-sdk/typescript
| `options.alwaysLoad` | `boolean` | When `true`, every tool from this server stays in the initial prompt instead of being deferred behind [tool search](/docs/en/agent-sdk/tool-sea
| `options.alwaysLoad` | `boolean` | When `true`, this server's tools stay in the initial prompt instead of being deferred behind [tool search](/docs/en/agent-sdk/tool-search). Com
`limit` sets the most artifacts a listing returns, from 1 to 200. A `limit` above 50 requires Agent SDK v0.3.292 or later. Without `limit`, a listing returns up to 25.
total?: number;
+7 −1 lines
Upstream edited 8 Oct 2026 20:28 UTC Recorded here 8 Oct 2026 20:37 UTC
claude-code
hooks
±changed
+185−25
claude-codechanged
hooks
| `Elicitation` | Yes | Denies the elicitation |
| `Elicitation` | Yes | Declines the request, and no dialog appears |
| Elicitation | `hookSpecificOutput` | `action` (accept/decline/cancel), `content` (form field values for accept) |
| ElicitationResult | `hookSpecificOutput` | `action` (accept/decline/cancel), `content` (form field values override) |
| Elicitation, ElicitationResult | `hookSpecificOutput` or top-level `decision` | `action` (accept/decline/cancel), `content` (form field values). `decision: "block"` also [decline
+185 −25 lines
Upstream edited 8 Oct 2026 20:22 UTC Recorded here 8 Oct 2026 20:37 UTC
claude-code
plugins/mods/overview
±changed
+1−1
claude-codechanged
plugins/mods/overview
* **Desktop app**: in a local session in the Code tab, enter `/status` and read the **Claude Code** row, which shows a version such as `2.1.286`. If yours is older, update the Desk
* **Desktop app**: in a local session in the Code tab, enter `/status` and read the **Claude Code** row, which shows a version such as `2.1.286`. If yours is older, [update the Des
+1 −1 lines
Upstream edited 8 Oct 2026 20:16 UTC Recorded here 8 Oct 2026 20:37 UTC
claude-code
desktop
±changed
+9−1
claude-codechanged
desktop
* **Local sessions on this machine**: a managed settings file deployed to disk applies. Managed settings pushed remotely through the admin console also reach these sessions on Anth
* **Local sessions on this machine**: a managed settings file deployed to disk applies. Managed settings pushed remotely through the admin console also reach these sessions on Anth
#### Claude Code version in the Code tab
To see which version of Claude Code a session runs, type `/status` in a local session in the **Code** tab and read the **Claude Code** row, which shows a version such as `2.1.286`.
+9 −1 lines
Upstream edited 8 Oct 2026 20:16 UTC Recorded here 8 Oct 2026 20:37 UTC
claude-code
model-config
±changed
+1−1
claude-codechanged
model-config
* 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 ke
* Delivery from the admin console also requires the session to fetch with an [eligible login](/docs/en/server-managed-settings#platform-availability) to your organization or an OAu
+1 −1 lines
Upstream edited 8 Oct 2026 20:16 UTC Recorded here 8 Oct 2026 20:37 UTC
claude-code
managed-settings
±changed
+1−1
claude-codechanged
managed-settings
1. Remote settings, delivered from claude.ai as [server-managed settings](/docs/en/server-managed-settings) or by a [Claude apps gateway](/docs/en/claude-apps-gateway). Claude Code
1. Remote settings, delivered from claude.ai as [server-managed settings](/docs/en/server-managed-settings) or by a [Claude apps gateway](/docs/en/claude-apps-gateway). Claude Code
+1 −1 lines
Upstream edited 8 Oct 2026 20:16 UTC Recorded here 8 Oct 2026 20:37 UTC
claude-code
authentication
±changed
+0−2
claude-codechanged
authentication
If your organization uses [server-managed settings](/docs/en/server-managed-settings), they apply to this sign-in on Claude Code v2.1.257 or later.
+0 −2 lines
Upstream edited 8 Oct 2026 20:16 UTC Recorded here 8 Oct 2026 20:37 UTC
claude-code
debug-your-config
±changed
+12−1
claude-codechanged
debug-your-config
Start with [`claude --safe-mode`](/docs/en/cli-reference#cli-flags), which launches a session with all customizations disabled, including `CLAUDE.md`, skills, plugins, hooks, MCP s
Start with [`claude --safe-mode`](/docs/en/cli-reference#cli-flags), which launches a session with your customizations disabled, including:
* `CLAUDE.md`
* Skills, plugins, and hooks
+12 −1 lines
Upstream edited 8 Oct 2026 20:14 UTC Recorded here 8 Oct 2026 20:37 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 8 Oct 2026 20:07 UTC
claude-code
plugins/mods/troubleshoot
±changed
+9−1
claude-codechanged
plugins/mods/troubleshoot
### `the module failed without a message`
A [`Client`](/docs/en/plugins/mods/interface#when-a-client-fails) failed with an error that has no message, such as `throw new Error()`. The line in its place reads like `my-mod: C
Find the throw in your `Client`'s code and give the error a message. The line then shows that message.
+9 −1 lines
Upstream edited 8 Oct 2026 20:01 UTC Recorded here 8 Oct 2026 20:07 UTC
claude-code
plugins/mods/interface
±changed
+8−0
claude-codechanged
plugins/mods/interface
<h3 id="when-a-client-fails">
When a `Client` fails
</h3>
+8 −0 lines
Upstream edited 8 Oct 2026 20:01 UTC Recorded here 8 Oct 2026 20:07 UTC
claude-code
changelog
±changed
+213−45
claude-codechanged
changelog
<Update label="2.1.295" description="October 8, 2026">
**Added**
* Added `onFailure: "block"` for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it through
+213 −45 lines
Upstream edited 8 Oct 2026 19:56 UTC Recorded here 8 Oct 2026 20:07 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
Opening the same session's row in [agent view](/docs/en/agent-view) shows `Press enter again to restart this session fresh` below the list instead, and a second `Enter` on the row
Opening the same session's row in [agent view](/docs/en/agent-view) shows `Press enter again to restart this session fresh` below the list instead, and a second `Enter` on the row
+1 −1 lines
Upstream edited 8 Oct 2026 19:47 UTC Recorded here 8 Oct 2026 20:07 UTC
claude-code
hooks
±changed
+2−0
claude-codechanged
hooks
In a prompt or [agent hook](#agent-based-hooks), you can write the `prompt` as a rule about what to block or allow, such as "Block any Bash command that reads `.env` files", or as
+2 −0 lines
Upstream edited 8 Oct 2026 19:46 UTC Recorded here 8 Oct 2026 20:07 UTC
claude-code
plugins/mods/reference
±changed
+2−1
claude-codechanged
plugins/mods/reference
| `next.error`, `next.called` | In a `.catch` handler only. `next.error.kind` is `throw` or `timeout`, `next.error.message` is the error's text, and `next.called` is `true` when th
| `next.error` | In a `.catch` handler only. `kind` is `throw` or `timeout` when the hook failed, and `message` is the error's text. `kind` is `re-entry` when the hook was skipped
| `next.called` | In a `.catch` handler only. `true` when the hook had called `next`. |
+2 −1 lines
Upstream edited 8 Oct 2026 19:43 UTC Recorded here 8 Oct 2026 20:07 UTC
claude-code
plugins/mods/events
±changed
+4−4
claude-codechanged
plugins/mods/events
// next.error.kind is 'throw' or 'timeout', which says how guard failed
// next.error.kind says why the handler was asked, such as 'throw' or 'timeout'
While `guard` works, the handler never runs. When `guard` throws or times out on a Bash call, Claude Code calls the handler with the same event:
* **`guard` failed before it called `next`**: the command doesn't run, and Claude reads the `deny` text with `throw` or `timeout` at the end
+4 −4 lines
Upstream edited 8 Oct 2026 19:43 UTC Recorded here 8 Oct 2026 20:07 UTC
claude-code
agent-sdk/typescript
±changed
+2−2
claude-codechanged
agent-sdk/typescript
* `resume_reason`: why Claude Code re-ran this turn after a restart interrupted it. Present on both arms, and only on such a re-run. See [`resume_reason`](#resume_reason).
* `resume_reason`: why Claude Code re-ran this turn after a restart interrupted it. Present on both arms. See [`resume_reason`](#resume_reason).
The value is a short lowercase token naming why the turn was re-run, such as `interrupted_turn`. The field is absent on every other turn.
The value is a short lowercase token naming why the turn was re-run, such as `interrupted_turn`.
+2 −2 lines
Upstream edited 8 Oct 2026 19:37 UTC Recorded here 8 Oct 2026 20:07 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 8 Oct 2026 19:37 UTC
claude-code
plugins/mods/events
±changed
+2−0
claude-codechanged
plugins/mods/events
To stop a prompt, return `{ drop: 'the reason' }` without calling `next`. If your hook returns a `drop` after its `next(e)` call let the prompt through, the turn still runs, and th
+2 −0 lines
Upstream edited 8 Oct 2026 19:31 UTC Recorded here 8 Oct 2026 19:37 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
Viewing a file with Bash affects edit eligibility only, not permissions. See [Read and Edit permission rules](/docs/en/permissions#read-and-edit) for which Bash commands your `Read
When Claude views a file this way, Claude Code also loads any [subdirectory `CLAUDE.md`](/docs/en/memory#how-claude-md-files-load) and [path-scoped rules](/docs/en/memory#path-spec
+1 −1 lines
Upstream edited 8 Oct 2026 19:29 UTC Recorded here 8 Oct 2026 19:37 UTC
claude-code
memory
±changed
+2−2
claude-codechanged
memory
Claude also discovers `CLAUDE.md` and `CLAUDE.local.md` files in subdirectories under your current working directory. Instead of loading them at launch, Claude Code includes them w
Claude also discovers `CLAUDE.md` and `CLAUDE.local.md` files in subdirectories under your current working directory. Instead of loading them at launch, Claude Code loads each one
Rules without a `paths` field are loaded unconditionally and apply to all files. Path-scoped rules trigger when Claude uses the Read, Write, or Edit tool on a file matching the pat
Rules without a `paths` field are loaded unconditionally and apply to all files. A path-scoped rule loads when Claude uses the Read, Write, or Edit tool on a matching file. It also
+2 −2 lines
Upstream edited 8 Oct 2026 19:29 UTC Recorded here 8 Oct 2026 19:37 UTC
claude-code
agent-view
±changed
+1−0
claude-codechanged
agent-view
* **A queued message can't move**: messages you [queued while Claude was working](/docs/en/interactive-mode#queue-messages-while-claude-works) move to the background session with t
+1 −0 lines
Upstream edited 8 Oct 2026 19:29 UTC Recorded here 8 Oct 2026 19:37 UTC
claude-code
plugins/mods/troubleshoot
±changed
+8−0
claude-codechanged
plugins/mods/troubleshoot
### `its session.start ran again in a fresh copy`
The line starts with the mod's name and names a `$.prompt.submit`, `$.command.run`, or `$.agent.spawn` call, as in `first-mod: its session.start ran again in a fresh copy; the $.pr
There's nothing to fix.
+8 −0 lines
Upstream edited 8 Oct 2026 19:27 UTC Recorded here 8 Oct 2026 19:37 UTC
claude-code
agent-sdk/typescript
±changed
+5−1
claude-codechanged
agent-sdk/typescript
| "bypass_root";
| "bypass_root"
| "org_config_required_unavailable"
| "org_config_refused";
| `org_config_required_unavailable` | The session needs the organization's policies and managed settings before it can start, and they couldn't be loaded, for example because of a
+5 −1 lines
Upstream edited 8 Oct 2026 19:27 UTC Recorded here 8 Oct 2026 19:37 UTC
claude-code
plugins/mods/reference
±changed
+2−1
claude-codechanged
plugins/mods/reference
Hooks and mods API calls run under time and size limits. Claude Code skips a hook that exceeds a time limit and rejects a call that exceeds a size limit.
Hooks and mods API calls run under time and size limits. Claude Code skips a hook that exceeds a time limit.
| A `Code`'s `language` or `path`, a `Select` option's `value`, or a `Client`'s `module` | 10,000 characters. If one is longer, Claude Code [draws its own version of the site](/doc
+2 −1 lines
Upstream edited 8 Oct 2026 19:26 UTC Recorded here 8 Oct 2026 19:37 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 8 Oct 2026 19:07 UTC
claude-code
changelog
±changed
+6503−4838
claude-codechanged
changelog
No line of the body moved in this read.
+6503 −4838 lines
Upstream edited 8 Oct 2026 19:00 UTC Recorded here 8 Oct 2026 19:07 UTC
claude-code
monitoring-usage
±changed
+3−3
claude-codechanged
monitoring-usage
* Up to 20 plugin-emitted metric keys. Names match `^[a-z][a-z0-9_]{0,39}$`. Values are boolean or number.
* Up to 20 plugin-emitted metric keys. Names match `^[a-z][a-z0-9_]{0,39}$`. Values are Boolean or number.
* `enabled_via_override`: `true` when [`CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL`](/docs/en/env-vars) is set. Emitted as a boolean, not a string. Present on `session` survey eve
* `enabled_via_override`: `true` when [`CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL`](/docs/en/env-vars) is set. Emitted as a Boolean, not a string. Present on `session` survey eve
* `managed_settings.settings_truncated` (when `managed_settings.settings` is present): `true` when Claude Code cut `managed_settings.settings` at 8 KB, `false` otherwise. Emitted a
+3 −3 lines
Upstream edited 8 Oct 2026 19:00 UTC Recorded here 8 Oct 2026 19:07 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
If you're building an MCP server, you can mark a tool as requiring explicit approval on every call by setting `_meta["anthropic/requiresUserInteraction"]` to `true` in the tool's `
If you're building an MCP server, you can mark a tool as requiring explicit approval on every call by setting `_meta["anthropic/requiresUserInteraction"]` to `true` in the tool's `
+1 −1 lines
Upstream edited 8 Oct 2026 19:00 UTC Recorded here 8 Oct 2026 19:07 UTC
claude-code
managed-settings
±changed
+2−2
claude-codechanged
managed-settings
* An invalid `disableAllHooks`, even a quoted boolean, is dropped with a warning, because enforcing `true` would also unload the hooks your own managed settings deploy.
* For every other boolean key the rule covers, the string `"true"` or `"false"` reads as that boolean, with a notice in `/status` asking you to drop the quotes.
* An invalid `disableAllHooks`, even a quoted Boolean, is dropped with a warning, because enforcing `true` would also unload the hooks your own managed settings deploy.
* For every other Boolean key the rule covers, the string `"true"` or `"false"` reads as that Boolean, with a notice in `/status` asking you to drop the quotes.
+2 −2 lines
Upstream edited 8 Oct 2026 19:00 UTC Recorded here 8 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 8 Oct 2026 18:45 UTC
claude-code
model-config
±changed
+33−35
claude-codechanged
model-config
| **`opus[1m]`** | Uses Opus with a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes-by-model) for long s
| **`opus[1m]`** | Uses Opus with a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes-by-model) for long s
The fallback model must also have a context window at least as large as the session's, or Claude Code doesn't switch and the flagged request ends with the same refusal. On these pr
<span id="sonnet-5-5-and-sonnet-5-context-window" />
+33 −35 lines
Upstream edited 8 Oct 2026 18:41 UTC Recorded here 8 Oct 2026 18:45 UTC
claude-code
microsoft-foundry
±changed
+18−0
claude-codechanged
microsoft-foundry
## 1M token context window
On Microsoft Foundry, when Claude Code can tell which model your deployment serves, Fable models, Sonnet 5 and later, and Opus 4.7 and later run with the [1M token context window](
This `settings.json` entry tells Claude Code that a deployment named `team-opus-prod` serves Opus 4.8:
+18 −0 lines
Upstream edited 8 Oct 2026 18:41 UTC Recorded here 8 Oct 2026 18:45 UTC
claude-code
google-vertex-ai
±changed
+5−3
claude-codechanged
google-vertex-ai
Claude Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes
The [setup wizard](#sign-in-with-agent-platform) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. Se
Fable models, Sonnet 5 and later, and Opus 4.7 and later run with the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window
+5 −3 lines
Upstream edited 8 Oct 2026 18:41 UTC Recorded here 8 Oct 2026 18:45 UTC
claude-code
context-window
±changed
+0−2
claude-codechanged
context-window
Sonnet 5.5 and Sonnet 5 run with the 1M context window and have no `[1m]` variant to select. See [Sonnet 5.5 and Sonnet 5 context window](/docs/en/model-config#sonnet-5-5-and-sonne
+0 −2 lines
Upstream edited 8 Oct 2026 18:41 UTC Recorded here 8 Oct 2026 18:45 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.