2026年6月10日 06:34

35 ファイル変更+188-78

この更新の概要

Opus 4.8やFable 5といった新しいモデルへの対応と、1Mコンテキスト利用時のクレジット要件に関するエラー解説が追加されました。環境変数CLAUDE_CONFIG_DIRによる設定ディレクトリのカスタマイズや、リモートコントロール機能のステータスインジケーター表示などの新機能が反映されています。agent-sdkにおけるPythonおよびTypeScriptのコード例が更新され、ストリーミング時のエラーハンドリングやセッション管理の仕様がより詳細に記述されました。また、ローカル設定ファイルであるsettings.local.jsonのgit管理に関する推奨事項が整理されています。

agent-sdk/agent-loop+2-2

Opus 4.8におけるeffortパラメータの推奨設定が追加され、SDKごとのデフォルト動作の差異が修正されました。

@@ -160,10 +160,10 @@ The `effort` option controls how much reasoning Claude applies. Lower effort lev

| `"low"` | Minimal reasoning, fast responses | File lookups, listing directories |

| `"medium"` | Balanced reasoning | Routine edits, standard tasks |

| `"high"` | Thorough analysis | Refactors, debugging |

| `"xhigh"` | Extended reasoning depth | Coding and agentic tasks; recommended on Opus 4.7 |

| `"xhigh"` | Extended reasoning depth | Coding and agentic tasks; recommended on Opus 4.8 and Opus 4.7 |

| `"max"` | Maximum reasoning depth | Multi-step problems requiring deep analysis |

If you don't set `effort`, the Python SDK leaves the parameter unset and defers to the model's default behavior. The TypeScript SDK defaults to `"high"`.

If you don't set `effort`, both SDKs leave the parameter unset and defer to the model's default behavior.

`effort` trades latency and token cost for reasoning depth within each response. [Extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) is a separate feature that produces visible chain-of-thought blocks in the output. They are independent: you can set `effort: "low"` with extended thinking enabled, or `effort: "max"` without it.

agent-sdk/cost-tracking+21-6

PythonおよびTypeScript SDKにおける、クエリ実行とコスト追跡の具体的な実装コード例が追加されました。

@@ -215,15 +215,26 @@ To request a 1-hour TTL on cache writes, set the [`ENABLE_PROMPT_CACHING_1H`](/e

The following example enables 1-hour TTL for an agent running on Bedrock:

```python Python theme={null}

options = ClaudeAgentOptions(

env={

"CLAUDE_CODE_USE_BEDROCK": "1",

"ENABLE_PROMPT_CACHING_1H": "1",

)

from claude_agent_sdk import ClaudeAgentOptions, query

import asyncio

async def main():

options = ClaudeAgentOptions(

env={

"CLAUDE_CODE_USE_BEDROCK": "1",

"ENABLE_PROMPT_CACHING_1H": "1",

)

async for message in query(prompt="Summarize this project", options=options):

print(message)

asyncio.run(main())

```

```typescript TypeScript theme={null}

import { query } from "@anthropic-ai/claude-agent-sdk";

const options = {

env: {

...process.env,

@@ -231,6 +242,10 @@ const options = {

ENABLE_PROMPT_CACHING_1H: "1",

};

for await (const message of query({ prompt: "Summarize this project", options })) {

console.log(message);

}

```

Cache writes with a 1-hour TTL are billed at a higher rate than 5-minute writes, so enabling this trades higher write cost for more cache reads. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. Claude subscription users already receive 1-hour TTL automatically and do not need to set this variable.

agent-sdk/migration-guide+12-6

移行手順に破壊的変更の確認ステップが追加され、TypeScript SDKのクエリ呼び出し例が更新されました。

@@ -73,7 +73,9 @@ After:

}

```

That's it! No other code changes are required.

**5. Review [breaking changes](#breaking-changes)**

Make any code changes needed to complete the migration.

### For Python Projects

@@ -152,12 +154,14 @@ options = ClaudeAgentOptions(model="claude-opus-4-7", permission_mode="acceptEdi

**Migration:**

```typescript TypeScript theme={null}

import { query } from "@anthropic-ai/claude-agent-sdk";

// BEFORE (v0.0.x) - Used Claude Code's system prompt by default

const result = query({ prompt: "Hello" });

const before = query({ prompt: "Hello" });

// AFTER (v0.1.0) - Uses minimal system prompt by default

// To get the old behavior, explicitly request Claude Code's preset:

const result = query({

const presetResult = query({

prompt: "Hello",

options: {

systemPrompt: { type: "preset", preset: "claude_code" }

@@ -165,7 +169,7 @@ const result = query({

});

// Or use a custom system prompt:

const result = query({

const customResult = query({

prompt: "Hello",

options: {

systemPrompt: "You are a helpful coding assistant"

@@ -209,7 +213,9 @@ This default was briefly changed in v0.1.0 and then reverted, so no migration ac

To run isolated from filesystem settings, pass an empty array:

```typescript TypeScript theme={null}

const result = query({

import { query } from "@anthropic-ai/claude-agent-sdk";

const isolatedResult = query({

prompt: "Hello",

options: {

settingSources: [] // No filesystem settings loaded

@@ -217,7 +223,7 @@ const result = query({

});

// Or load only specific sources:

const result = query({

const projectOnlyResult = query({

prompt: "Hello",

options: {

settingSources: ["project"] // Only project settings

agent-sdk/python+5-5

modelおよびeffortパラメータの説明が詳細化され、Opus 4.8を含む1Mコンテキスト対応モデルのリストが更新されました。

@@ -787,7 +787,7 @@ class ClaudeAgentOptions:

| `max_budget_usd` | `float \| None` | `None` | Stop the query when the client-side cost estimate reaches this USD value. Compared against the same estimate as `total_cost_usd`; see [Track cost and usage](/en/agent-sdk/cost-tracking) for accuracy caveats |

| `disallowed_tools` | `list[str]` | `[]` | Tools to deny. A bare name such as `"Bash"` removes the tool from Claude's context. A scoped rule such as `"Bash(rm *)"` leaves the tool available and denies matching calls in every permission mode, including `bypassPermissions`. See [Permissions](/en/agent-sdk/permissions#allow-and-deny-rules) |

| `output_format` | `dict[str, Any] \| None` | `None` | Output format for structured responses (e.g., `{"type": "json_schema", "schema": {...}}`). See [Structured outputs](/en/agent-sdk/structured-outputs) for details |

@@ -814,7 +814,7 @@ class ClaudeAgentOptions:

| `skills` | `list[str] \| Literal["all"] \| None` | `None` | Skills available to the session. Pass `"all"` to enable every discovered skill, or a list of skill names. When set, the SDK adds the Skill tool to `allowed_tools` automatically. If you also pass `tools`, include `"Skill"` in that list. See [Skills](/en/agent-sdk/skills) |

| `session_store` | [`SessionStore`](/en/agent-sdk/session-storage#the-sessionstore-interface) ` \| None` | `None` | Mirror session transcripts to an external backend so any host can resume them. See [Persist sessions to external storage](/en/agent-sdk/session-storage) |

| `session_store_flush` | `Literal["batched", "eager"]` | `"batched"` | When to flush mirrored transcript entries to `session_store`. `"batched"` flushes once per turn or when the buffer fills; `"eager"` triggers a background flush after every frame. Ignored when `session_store` is `None` |

@@ -885,7 +885,7 @@ SettingSource = Literal["user", "project", "local"]

| :- | :- | :- |

| `"user"` | Global user settings | `~/.claude/settings.json` |

| `"project"` | Shared project settings (version controlled) | `.claude/settings.json` |

| `"local"` | Local project settings (gitignored) | `.claude/settings.local.json` |

| `"local"` | Local project settings (not version controlled) | `.claude/settings.local.json` |

#### Default behavior

@@ -1059,7 +1059,7 @@ EffortLevel = Literal[

"low", # Minimal thinking, fastest responses

"medium", # Moderate thinking

"high", # Deep reasoning

"xhigh", # Extended reasoning (Opus 4.7 only; falls back to "high" on other models)

"xhigh", # Extended reasoning (Opus 4.8 and Opus 4.7; falls back to "high" on other models)

"max", # Maximum effort

]

```

@@ -1260,7 +1260,7 @@ SdkBeta = Literal["context-1m-2025-08-07"]

Use with the `betas` field in `ClaudeAgentOptions` to enable beta features.

The `context-1m-2025-08-07` beta is retired as of April 30, 2026. Passing this header with Claude Sonnet 4.5 or Sonnet 4 has no effect, and requests that exceed the standard 200k-token context window return an error. To use a 1M-token context window, migrate to [Claude Sonnet 4.6, Claude Opus 4.6, or Claude Opus 4.7](https://platform.claude.com/docs/en/about-claude/models/overview), which include 1M context at standard pricing with no beta header required.

The `context-1m-2025-08-07` beta is retired as of April 30, 2026. Passing this header with Claude Sonnet 4.5 or Sonnet 4 has no effect, and requests that exceed the standard 200k-token context window return an error. To use a 1M-token context window, migrate to [Claude Sonnet 4.6, Claude Opus 4.6, Claude Opus 4.7, or Claude Opus 4.8](https://platform.claude.com/docs/en/about-claude/models/overview), which include 1M context at standard pricing with no beta header required.

### `McpSdkServerConfig`

agent-sdk/session-storage+2-0

セッション再開時にコンテキストが保持されていることを確認するための説明文が追記されました。

@@ -141,6 +141,8 @@ async def main():

asyncio.run(main())

```

The second query prints a summary of the files from the first query, which shows the agent resumed with full context from the store.

## Write your own adapter

Implement `append` and `load` against your backend. Add `listSessions`, `delete`, and `listSubkeys` if you want `listSessions()`, `deleteSession()`, and subagent resume to work against the store.

agent-sdk/sessions+18-4

CLAUDE_CONFIG_DIR環境変数によるセッション保存先の変更対応や、セッションのフォークに関する詳細な挙動が記述されました。

@@ -203,6 +203,10 @@ async for message in query(

```

```typescript TypeScript theme={null}

import { query } from "@anthropic-ai/claude-agent-sdk";

const sessionId = "..."; // The ID you captured in the previous example

// Earlier session analyzed the code; now build on that analysis

for await (const message of query({

prompt: "Now implement the refactoring you suggested",

@@ -217,7 +221,9 @@ for await (const message of query({

}

```

If a `resume` call returns a fresh session instead of the expected history, the most common cause is a mismatched `cwd`. Sessions are stored under `~/.claude/projects/<encoded-cwd>/*.jsonl`, where `<encoded-cwd>` is the absolute working directory with every non-alphanumeric character replaced by `-` (so `/Users/me/proj` becomes `-Users-me-proj`). If your resume call runs from a different directory, the SDK looks in the wrong place. The session file also needs to exist on the current machine.

You should see a response that builds on the earlier analysis instead of starting fresh. That confirms the agent resumed the session with its prior context intact.

If a `resume` call returns a fresh session instead of the expected history, the most common cause is a mismatched `cwd`. Sessions are stored under `~/.claude/projects/<encoded-cwd>/*.jsonl`, or under `$CLAUDE_CONFIG_DIR/projects/<encoded-cwd>/*.jsonl` if you set the `CLAUDE_CONFIG_DIR` environment variable, where `<encoded-cwd>` is the absolute working directory with every non-alphanumeric character replaced by `-` (so `/Users/me/proj` becomes `-Users-me-proj`). If your resume call runs from a different directory, the SDK looks in the wrong place. The session file also needs to exist on the current machine.

To resume sessions across machines or in serverless environments, mirror transcripts to shared storage with a [`SessionStore` adapter](/en/agent-sdk/session-storage).

@@ -233,10 +239,11 @@ This example builds on [Capture the session ID](#capture-the-session-id): you've

# Fork: branch from session_id into a new session

forked_id = None

async for message in query(

prompt="Instead of JWT, implement OAuth2 for the auth module",

prompt="Instead of JWT, outline how OAuth2 would work for the auth module",

options=ClaudeAgentOptions(

resume=session_id,

fork_session=True,

max_turns=5,

if isinstance(message, ResultMessage):

@@ -256,14 +263,19 @@ async for message in query(

```

```typescript TypeScript theme={null}

import { query } from "@anthropic-ai/claude-agent-sdk";

const sessionId = "..."; // The ID you captured in the previous example

// Fork: branch from sessionId into a new session

let forkedId: string | undefined;

for await (const message of query({

prompt: "Instead of JWT, implement OAuth2 for the auth module",

prompt: "Instead of JWT, outline how OAuth2 would work for the auth module",

options: {

resume: sessionId,

forkSession: true

forkSession: true,

maxTurns: 5

}

})) {

if (message.type === "system" && message.subtype === "init") {

@@ -287,6 +299,8 @@ for await (const message of query({

}

```

You should see that `forkedId` differs from the original session ID. Resuming the original session still continues the JWT thread, which confirms the fork did not modify the original history.

## Resume across hosts

Session files are local to the machine that created them. To resume a session on a different host (CI workers, ephemeral containers, serverless), you have two options:

agent-sdk/streaming-output+1-0

ストリーミング出力のイベントに、最初のトークンまでの時間を示すttft_msプロパティが追加されました。

@@ -91,6 +91,7 @@ type SDKPartialAssistantMessage = {

parent_tool_use_id: string | null;

uuid: UUID;

session_id: string;

ttft_ms?: number; // Time to first token in ms, present only on message_start events

};

```

agent-sdk/streaming-vs-single-mode+6-0

SDK実行時に例外が発生した場合のエラー表示の仕様と、ループ内でのエラーハンドリング方法が詳しく解説されています。

@@ -193,6 +193,10 @@ async def streaming_analysis():

asyncio.run(streaming_analysis())

```

In the TypeScript SDK, if your message generator throws, for example when a file it reads is missing, the stream ends with an error that reads `Claude Code process aborted by user` instead of the original error, so check the code inside your generator first when you see that message. The error may also be preceded by a long minified line of bundled SDK source, so read to the end of the output for the error text.

In the Python SDK, a generator exception is logged at debug level and the session stalls without raising, so if a streaming session hangs with no output, enable debug logging and check your generator.

## Single Message Input

Single message input is simpler but more limited.

@@ -214,6 +218,8 @@ Single message input mode does **not** support:

- Real-time interruption

- Natural multi-turn conversations

If a query ends with an error result, such as `error_max_turns`, a single message `query()` call raises an error that includes the failure text after yielding the final result message, so wrap the loop in a try block if your code needs to continue. See [Handle the result](/en/agent-sdk/agent-loop#handle-the-result) for the result subtypes.

### Implementation Example

```typescript TypeScript theme={null}

agent-sdk/subagents+1-1

サブエージェントで使用可能なモデルのエイリアスにfableが追加されました。

@@ -162,7 +162,7 @@ Focus on:

| `model` | `string` | No | Model override for this agent. Accepts an alias such as `'sonnet'`, `'opus'`, `'haiku'`, `'inherit'`, or a full model ID. Defaults to main model if omitted |

| `model` | `string` | No | Model override for this agent. Accepts an alias such as `'fable'`, `'opus'`, `'sonnet'`, `'haiku'`, `'inherit'`, or a full model ID. Defaults to main model if omitted |

agent-sdk/typescript+7-6

effortパラメータのデフォルト値がモデル依存に変更され、タイムスタンププロパティなどの型定義が更新されました。

@@ -406,7 +406,7 @@ Configuration object for the `query()` function.

| `disallowedTools` | `string[]` | `[]` | Tools to deny. A bare name such as `"Bash"` removes the tool from Claude's context. A scoped rule such as `"Bash(rm *)"` leaves the tool available and denies matching calls in every permission mode, including `bypassPermissions`. See [Permissions](/en/agent-sdk/permissions#allow-and-deny-rules) |

| `env` | `Record<string, string \| undefined>` | `process.env` | Environment variables. When set, this replaces the subprocess environment instead of merging with `process.env`, so pass `{ ...process.env, YOUR_VAR: 'value' }` to keep inherited variables like `PATH`. See [Handle slow or stalled API responses](#handle-slow-or-stalled-api-responses) for an example of this pattern, and [Environment variables](/en/env-vars) for variables the underlying CLI reads. Set `CLAUDE_AGENT_SDK_CLIENT_APP` to identify your app in the User-Agent header |

@@ -424,7 +424,7 @@ Configuration object for the `query()` function.

| `mcpServers` | `Record<string, [`McpServerConfig`](#mcpserverconfig)>` | `{}` | MCP server configurations |

| `onElicitation` | `(request: ElicitationRequest, options: { signal: AbortSignal }) => Promise<ElicitationResult>` | `undefined` | Callback for handling MCP elicitation requests. Called when an MCP server requests user input and no hook handles it first. When not provided, unhandled elicitation requests are declined automatically |

| `outputFormat` | `{ type: 'json_schema', schema: JSONSchema }` | `undefined` | Define output format for agent results. See [Structured outputs](/en/agent-sdk/structured-outputs) for details |

| `outputStyle` | `string` | `undefined` | Not an `Options` field. Set `outputStyle` in the inline [`settings`](/en/settings) object or a settings file instead. See [Activate an output style](/en/agent-sdk/modifying-system-prompts#activate-an-output-style) |

@@ -629,7 +629,7 @@ type AgentDefinition = {

| `tools` | No | Array of allowed tool names. If omitted, inherits all tools from parent. To preload Skills into the agent's context, use the `skills` field rather than listing `'Skill'` here |

| `disallowedTools` | No | Array of tool names to explicitly disallow for this agent |

| `prompt` | Yes | The agent's system prompt |

| `model` | No | Model override for this agent. Accepts an alias such as `'sonnet'`, `'opus'`, `'haiku'`, `'inherit'`, or a full model ID. If omitted or `'inherit'`, uses the main model |

| `model` | No | Model override for this agent. Accepts an alias such as `'fable'`, `'opus'`, `'sonnet'`, `'haiku'`, `'inherit'`, or a full model ID. If omitted or `'inherit'`, uses the main model |

| `mcpServers` | No | MCP server specifications for this agent |

| `skills` | No | Array of skill names to preload into the agent context |

| `initialPrompt` | No | Auto-submitted as the first user turn when this agent runs as the main thread agent |

@@ -662,7 +662,7 @@ type SettingSource = "user" | "project" | "local";

| :- | :- | :- |

| `'user'` | Global user settings | `~/.claude/settings.json` |

| `'project'` | Shared project settings (version controlled) | `.claude/settings.json` |

| `'local'` | Local project settings (gitignored) | `.claude/settings.local.json` |

| `'local'` | Local project settings (not version controlled) | `.claude/settings.local.json` |

#### Default behavior

@@ -1134,6 +1134,7 @@ type SDKPartialAssistantMessage = {

parent_tool_use_id: string | null;

uuid: UUID;

session_id: string;

ttft_ms?: number; // Time to first token in ms, present only on message_start events

};

```

@@ -2689,7 +2690,7 @@ type PermissionBehavior = "allow" | "deny" | "ask";

type PermissionUpdateDestination =

| "userSettings" // Global user settings

| "projectSettings" // Per-directory project settings

| "localSettings" // Gitignored local settings

| "localSettings" // Local project settings

| "session" // Current session only

| "cliArg"; // CLI argument

```

@@ -2719,7 +2720,7 @@ Available beta features that can be enabled via the `betas` option. See [Beta he

type SdkBeta = "context-1m-2025-08-07";

```

The `context-1m-2025-08-07` beta is retired as of April 30, 2026. Passing this value with Claude Sonnet 4.5 or Sonnet 4 has no effect, and requests that exceed the standard 200k-token context window return an error. To use a 1M-token context window, migrate to [Claude Sonnet 4.6, Claude Opus 4.6, or Claude Opus 4.7](https://platform.claude.com/docs/en/about-claude/models/overview), which include 1M context at standard pricing with no beta header required.

The `context-1m-2025-08-07` beta is retired as of April 30, 2026. Passing this value with Claude Sonnet 4.5 or Sonnet 4 has no effect, and requests that exceed the standard 200k-token context window return an error. To use a 1M-token context window, migrate to [Claude Sonnet 4.6, Claude Opus 4.6, Claude Opus 4.7, or Claude Opus 4.8](https://platform.claude.com/docs/en/about-claude/models/overview), which include 1M context at standard pricing with no beta header required.

### `SlashCommand`

agent-teams+3-3

チームメイトの終了方法や、自動クリーンアップの挙動、設定ディレクトリの生存期間に関する説明が追加されました。

@@ -153,7 +153,7 @@ Task claiming uses file locking to prevent race conditions when multiple teammat

### Shut down teammates

To gracefully end a teammate's session:

To gracefully end a teammate's session, refer to it by name. For example, with a teammate named researcher:

```text

Ask the researcher teammate to shut down

@@ -169,7 +169,7 @@ When you're done, ask the lead to clean up:

Clean up the team

```

This removes the shared team resources. When the lead runs cleanup, it checks for active teammates and fails if any are still running, so shut them down first.

This removes the shared team resources. When the lead runs cleanup, it checks for active teammates and fails if any are still running, so shut them down first. Claude often cleans up on its own when the team's work is done, so a later cleanup request may report that there is nothing to clean up.

Always use the lead to clean up. Teammates should not run cleanup because their team context may not resolve correctly, potentially leaving resources in an inconsistent state.

@@ -214,7 +214,7 @@ Teams and tasks are stored locally:

- **Team config**: `~/.claude/teams/{team-name}/config.json`

- **Task list**: `~/.claude/tasks/{team-name}/`

Claude Code generates both of these automatically when you create a team and updates them as teammates join, go idle, or leave. The team config holds runtime state such as session IDs and tmux pane IDs, so don't edit it by hand or pre-author it: your changes are overwritten on the next state update.

Claude Code generates both of these automatically when you create a team and updates them as teammates join, go idle, or leave. Both directories exist only while the team is active: they are removed when the team is cleaned up or when the session ends. The team config holds runtime state such as session IDs and tmux pane IDs, so don't edit it by hand or pre-author it: your changes are overwritten on the next state update.

To define reusable teammate roles, use [subagent definitions](#use-subagent-definitions-for-teammates) instead.

agent-view+1-1

エージェント一覧を表示するコマンドにおいて、ネストされたセッションの登録除外に関する記述が削除されました。

@@ -425,7 +425,7 @@ Every background session has a short ID you can use from the shell. The ID is pr

| :- | :- |

| `claude agents` | Open agent view |

| `claude agents --cwd <path>` | Open agent view scoped to sessions started under `<path>` |

| `claude agents --json` | Print active sessions as a JSON array and exit: every live session except nested interactive sessions launched from inside Claude Code, which do not register (see `CLAUDECODE` in [environment variables](/en/env-vars)), plus background sessions that are still working or blocked even when their process has exited. Add `--all` to also include completed background sessions. Each entry has `cwd`, `kind`, and `startedAt`. Background entries also have `id`, usable with `claude attach`/`logs`/`stop`, and `state`: one of `working`, `blocked`, `done`, `failed`, or `stopped`. `pid` and `status` are present only while the process is alive, plus `waitingFor` when status is `waiting`, which says what the session is blocked on, such as `permission prompt` or `input needed`; `sessionId` and `name` appear when set. Combine with `--cwd <path>` to filter |

| `claude agents --json` | Print active sessions as a JSON array and exit: every live session, plus background sessions that are still working or blocked even when their process has exited. Add `--all` to also include completed background sessions. Each entry has `cwd`, `kind`, and `startedAt`. Background entries also have `id`, usable with `claude attach`/`logs`/`stop`, and `state`: one of `working`, `blocked`, `done`, `failed`, or `stopped`. `pid` and `status` are present only while the process is alive, plus `waitingFor` when status is `waiting`, which says what the session is blocked on, such as `permission prompt` or `input needed`; `sessionId` and `name` appear when set. Combine with `--cwd <path>` to filter |

| `claude attach <id>` | Attach to a session in this terminal |

| `claude logs <id>` | Print the session's recent output |

| `claude stop <id>` | Stop a session. Also accepts `claude kill` |

auto-mode-config+1-1

settings.local.jsonの用途説明からgitignoredという限定的な表現が削除されました。

@@ -32,7 +32,7 @@ For rules that apply across projects, such as trusted infrastructure or organiza

| Scope | File | Use for |

| :- | :- | :- |

| One developer | `~/.claude/settings.json` | Personal trusted infrastructure |

| One project, one developer | `.claude/settings.local.json` | Per-project trusted buckets or services, gitignored |

| One project, one developer | `.claude/settings.local.json` | Per-project trusted buckets or services |

| Organization-wide | [Managed settings](/en/server-managed-settings) | Trusted infrastructure distributed to all developers |

| `--settings` flag or Agent SDK | Inline JSON | Per-invocation overrides for automation |

channels-reference+6-2

MCPサーバー利用時の同意ダイアログや、権限承認フローにおける具体的な動作確認手順が詳しく説明されています。

@@ -125,8 +125,12 @@ During the research preview, custom channels aren't on the allowlist, so start C

claude --dangerously-load-development-channels server:webhook

```

The first time you start a session in this project, Claude Code asks for consent before using the new server from `.mcp.json`. The dialog reports "New MCP server found in this project: webhook". Select **Use this MCP server** to continue.

When Claude Code starts, it reads your MCP config, spawns your `webhook.ts` as a subprocess, and the HTTP listener starts automatically on the port you configured (8788 in this example). You don't need to run the server yourself.

A dim notice below the startup banner confirms the channel is registered: `Channels (experimental) messages from server:webhook inject directly in this session · restart without --dangerously-load-development-channels to stop`.

If you see "blocked by org policy," your organization admin needs to [enable channels](/en/channels#enterprise-controls) first.

In a separate terminal, simulate a webhook by sending an HTTP POST with a message to your server. This example sends a CI failure alert to port 8788 (or whichever port you configured):

@@ -692,13 +696,13 @@ In the third, send a message that will make Claude try to run a command:

curl -d "list the files in this directory" -H "X-Sender: dev" localhost:8788

```

The local permission dialog opens in your Claude Code terminal. A moment later the prompt appears in the `/events` stream, including the five-letter ID. Approve it from the remote side:

Listing files is read-only, so Claude runs it without approval. The permission dialog opens when Claude calls the `reply` tool to send its answer back. The local dialog opens in your Claude Code terminal, and a moment later the prompt for `mcp__webhook__reply` appears in the `/events` stream, including the five-letter ID. Approve it from the remote side:

```bash

curl -d "yes <id>" -H "X-Sender: dev" localhost:8788

```

The local dialog closes and the tool runs. Claude's reply comes back through the `reply` tool and lands in the stream too.

The local dialog closes, the `reply` tool runs, and Claude's reply lands in the stream.

The three channel-specific pieces in this file:

claude-code-on-the-web+1-0

ウェブ版でのスキル管理仕様が明記され、リポジトリにコミットすべき設定ファイルについての説明が追加されました。

@@ -61,6 +61,7 @@ Cloud sessions start from a fresh clone of your repository. Anything committed t

| Your repo's `.claude/skills/`, `.claude/agents/`, `.claude/commands/` | Yes | Part of the clone |

| Plugins declared in `.claude/settings.json` | Yes | Installed at session start from the [marketplace](/en/plugin-marketplaces) you declared. Requires network access to reach the marketplace source |

| Your user `~/.claude/CLAUDE.md` | No | Lives on your machine, not in the repo |

| Your user `~/.claude/skills/`, `~/.claude/agents/`, `~/.claude/commands/` | No | Live on your machine, not in the repo. Commit them to the repo's `.claude/` directory instead. Skills you enable on claude.ai are loaded into cloud sessions automatically |

| Plugins enabled only in your user settings | No | User-scoped `enabledPlugins` lives in `~/.claude/settings.json`. Declare them in the repo's `.claude/settings.json` instead |

| MCP servers you added with `claude mcp add` | No | Those write to your local user config, not the repo. Declare the server in [`.mcp.json`](/en/mcp#project-scope) instead |

| Static API tokens and credentials | No | No dedicated secrets store exists yet. See below |

claude-directory+1-1

settings.local.jsonがClaude Codeによって作成された場合に限り自動的にgitignoreされる仕様が明記されました。

@@ -65,7 +65,7 @@ Click a filename to open that node in the explorer above.

| [`rules/*.md`](#ce-rules) | Project and global | ✓ | Topic-scoped instructions, optionally path-gated | [Rules](/en/memory#organize-rules-with-claude/rules/) |

| [`settings.local.json`](#ce-settings-local-json) | Project only | | Your personal overrides, gitignored when Claude Code creates it | [Settings scopes](/en/settings#settings-files) |

claude-platform-on-aws+2-1

AWSプラットフォームにおけるデフォルトモデルのエイリアスにfableが追加され、関連する環境変数が紹介されました。

@@ -139,11 +139,12 @@ Claude Platform on AWS is opt-in even when AWS credentials are present in your e

### 3. Pin model versions

Claude Platform on AWS uses the same model IDs as the direct Claude API. The default aliases `opus`, `sonnet`, and `haiku` resolve to Claude Code's built-in defaults for Claude Platform on AWS, which can lag the newest release. Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias resolves to Opus 4.7.

Claude Platform on AWS uses the same model IDs as the direct Claude API. 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 `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias resolves to Opus 4.7.

If you deploy Claude Code to a team, pin the model IDs explicitly so a new release doesn't move everyone at once:

```bash

export ANTHROPIC_DEFAULT_FABLE_MODEL=claude-fable-5

export ANTHROPIC_DEFAULT_OPUS_MODEL=claude-opus-4-7

export ANTHROPIC_DEFAULT_SONNET_MODEL=claude-sonnet-4-6

export ANTHROPIC_DEFAULT_HAIKU_MODEL=claude-haiku-4-5

env-vars+8-4

CLAUDE_CODE_ALWAYS_ENABLE_EFFORTなどの新変数の追加と、廃止されたセッション永続化用変数の情報が反映されました。

@@ -63,7 +63,7 @@ The file you choose controls who the variables apply to:

| :- | :- |

| `~/.claude/settings.json` | You, in every project |

| `.claude/settings.json` | Everyone working in the project, checked into source control |

| `.claude/settings.local.json` | You, in this project only, not checked in |

| `.claude/settings.local.json` | You, in this project only (add it to your gitignore if you create it by hand) |

| Managed settings | Everyone in your organization, deployed by an admin |

See [Settings files](/en/settings#settings-files) for where each file lives and [Settings precedence](/en/settings#settings-precedence) for how they combine when more than one sets the same variable.

@@ -127,7 +127,7 @@ Claude Code reads environment variables at startup, so changes take effect the n

| `BASH_MAX_OUTPUT_LENGTH` | Maximum number of characters in bash outputs before the full output is saved to a file and Claude receives the path plus a short preview. See [Bash tool behavior](/en/tools-reference#bash-tool-behavior) |

| `BASH_MAX_TIMEOUT_MS` | Maximum timeout the model can set for long-running bash commands (default: 600000, or 10 minutes) |

| `CCR_FORCE_BUNDLE` | Set to `1` to force [`claude --remote`](/en/claude-code-on-the-web#send-local-repositories-without-github) to bundle and upload your local repository even when GitHub access is available |

| `CLAUDECODE` | Set to `1` in subprocesses Claude Code spawns (Bash and PowerShell tools, tmux sessions, [hook](/en/hooks) commands, [status line](/en/statusline) commands, stdio [MCP server](/en/mcp) subprocesses). Use to detect when a script is running inside a subprocess spawned by Claude Code. A nested interactive `claude` TUI started this way, such as one driving the CLI in tmux, is automatically excluded from `--resume`, `--continue`, up-arrow history, and the `claude agents` list. Non-interactive `claude -p` sessions still persist. Set `CLAUDE_CODE_FORCE_SESSION_PERSISTENCE=1` to override this exclusion |

| `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` | Set to `1` to disable all built-in [subagent](/en/sub-agents) types such as Explore and Plan. Only applies in non-interactive mode (the `-p` flag). Useful for SDK users who want a blank slate |

| `CLAUDE_AGENT_SDK_MCP_NO_PREFIX` | Set to `1` to skip the `mcp__<server>__` prefix on tool names from SDK-created MCP servers. Tools use their original names. SDK usage only |

| `CLAUDE_ASYNC_AGENT_STALL_TIMEOUT_MS` | Stall timeout in milliseconds for background subagents. Default `600000` (10 minutes). The timer resets on each streaming progress event; if no progress arrives within the window, the subagent is aborted and the task is marked failed, surfacing any partial result to the parent |

@@ -137,6 +137,7 @@ Claude Code reads environment variables at startup, so changes take effect the n

| `CLAUDE_CODE_ACCESSIBILITY` | Set to `1` to keep the native terminal cursor visible and disable the inverted-text cursor indicator. Allows screen magnifiers like macOS Zoom to track cursor position |

| `CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD` | Set to `1` to load memory files from directories specified with `--add-dir`. Loads `CLAUDE.md`, `.claude/CLAUDE.md`, `.claude/rules/*.md`, and `CLAUDE.local.md`. By default, additional directories do not load memory files |

| `CLAUDE_CODE_ALT_SCREEN_FULL_REPAINT` | Set to `1` to repaint the entire screen on every frame in [fullscreen rendering](/en/fullscreen) instead of sending incremental updates. Use this if fullscreen mode shows stale or misplaced text fragments. Claude Code enables this automatically for background sessions and [agent view](/en/agent-view) on Windows |

| `CLAUDE_CODE_ALWAYS_ENABLE_EFFORT` | Set to `1` to send the [effort](/en/model-config#adjust-effort-level) parameter with every request, even when Claude Code does not recognize the model ID as effort-capable. Use this when routing through an [LLM gateway](/en/llm-gateway) or third-party provider that serves models under custom identifiers. Models that reject the effort parameter at the API, including Claude 3 models, Sonnet 4.0 and 4.5, Opus 4.0 and 4.1, and Haiku 4.5, are still excluded so requests do not fail |

| `CLAUDE_CODE_API_KEY_HELPER_TTL_MS` | Interval in milliseconds at which credentials should be refreshed (when using [`apiKeyHelper`](/en/settings#available-settings)) |

| `CLAUDE_CODE_ATTRIBUTION_HEADER` | Set to `0` to omit the attribution block (client version and prompt fingerprint) from the start of the system prompt. Disabling it improves prompt-cache hit rates when routing through an [LLM gateway](/en/llm-gateway). Anthropic API caching is unaffected |

| `CLAUDE_CODE_AUTO_COMPACT_WINDOW` | Set the context capacity in tokens used for auto-compaction calculations. Defaults to the model's context window: 200K for standard models or 1M for [extended context](/en/model-config#extended-context) models. Use a lower value like `500000` on a 1M model to treat the window as 500K for compaction purposes. The value is capped at the model's actual context window. `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` is applied as a percentage of this value. Setting this variable decouples the compaction threshold from the status line's `used_percentage`, which always uses the model's full context window |

@@ -187,7 +188,7 @@ Claude Code reads environment variables at startup, so changes take effect the n

| `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` | Set to `1` to enable [agent teams](/en/agent-teams). Agent teams are experimental and disabled by default |

| `CLAUDE_CODE_EXTRA_BODY` | JSON object to merge into the top level of every API request body. Useful for passing provider-specific parameters that Claude Code does not expose directly |

| `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS` | Override the default token limit for file reads. Useful when you need to read larger files in full |

| `CLAUDE_CODE_FORCE_SESSION_PERSISTENCE` | Set to `1` to force transcript persistence, prompt history, and `claude agents` registration even when this `claude` was launched from inside another Claude Code session. Use when an inherited `CLAUDECODE` value, for example from a tmux server first started by Claude Code, causes a genuine top-level session to be misclassified as nested |

| `CLAUDE_CODE_FORCE_SESSION_PERSISTENCE` | Removed in v2.1.170. This variable forced transcript persistence when an inherited `CLAUDECODE` value caused a top-level session to be misclassified as nested. The nested-session detection it overrode was removed in v2.1.170, so the variable no longer applies |

| `CLAUDE_CODE_FORCE_SYNC_OUTPUT` | Set to `1` to force-enable DEC private mode 2026 [synchronized output](https://gist.github.com/christianparpart/d8a62cc1ab659194337d73e399004036) when your terminal supports it but is not auto-detected. Useful for emulators such as Emacs `eat` that implement BSU/ESU but do not reply to the capability probe. Has no effect under tmux |

| `CLAUDE_CODE_FORK_SUBAGENT` | Set to `1` to make [forked subagents](/en/sub-agents#fork-the-current-conversation) the model's default, or `0` to disable them, overriding any server-side rollout. When enabled, Claude spawns a fork, a subagent that inherits the full conversation context instead of starting fresh, whenever it would otherwise use the general-purpose subagent, and all subagent spawns run in the background. The explicit [`/fork`](/en/commands) command works without this variable. Works in interactive mode and via the SDK or `claude -p` |

| `CLAUDE_CODE_GIT_BASH_PATH` | Windows only: path to the Git Bash executable (`bash.exe`). Use when Git Bash is installed but not in your PATH. See [Windows setup](/en/setup#set-up-on-windows) |

@@ -249,7 +250,7 @@ Claude Code reads environment variables at startup, so changes take effect the n

| `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB` | Set to `1` to strip Anthropic and cloud provider credentials from subprocess environments (Bash tool, hooks, MCP stdio servers). The parent Claude process keeps these credentials for API calls, but child processes cannot read them, reducing exposure to prompt injection attacks that attempt to exfiltrate secrets via shell expansion. On Linux, this also runs Bash subprocesses in an isolated PID namespace so they cannot read host process environments via `/proc`; as a side effect, `ps`, `pgrep`, and `kill` cannot see or signal host processes. `claude-code-action` sets this automatically when `allowed_non_write_users` is configured |

| `CLAUDE_CODE_SYNC_PLUGIN_INSTALL` | Set to `1` in non-interactive mode (the `-p` flag) to wait for plugin installation to complete before the first query. Without this, plugins install in the background and may not be available on the first turn. Combine with `CLAUDE_CODE_SYNC_PLUGIN_INSTALL_TIMEOUT_MS` to bound the wait |

| `CLAUDE_CODE_SYNC_PLUGIN_INSTALL_TIMEOUT_MS` | Timeout in milliseconds for synchronous plugin installation. When exceeded, Claude Code proceeds without plugins and logs an error. No default: without this variable, synchronous installation waits until complete |

| `CLAUDE_CODE_SYNC_SKILLS` | Set to `1` to download your enabled claude.ai skills into `~/.claude/skills/` before the first query and resync every 10 minutes. Applies only in non-interactive mode with the `-p` flag. Set automatically in [Claude Code on the web](/en/claude-code-on-the-web) sessions. Requires claude.ai authentication |

| `CLAUDE_CODE_SYNC_SKILLS` | Set to `1` to download your enabled claude.ai skills into `~/.claude/skills/` before the first query and resync every 10 minutes. Applies only in non-interactive mode with the `-p` flag. Requires claude.ai authentication. [Claude Code on the web](/en/claude-code-on-the-web) sessions receive your enabled claude.ai skills automatically; you don't need to set this there |

| `CLAUDE_CODE_SYNC_SKILLS_INSTALL_TIMEOUT_MS` | Timeout in milliseconds for a mid-session skills resync when `CLAUDE_CODE_SYNC_SKILLS` is set (default: 30000). Bounds the download triggered when the host requests a skill reload during the session. When exceeded, the resync stops and remaining downloads continue in the background |

| `CLAUDE_CODE_SYNC_SKILLS_WAIT_TIMEOUT_MS` | Timeout in milliseconds for the first query to wait on the initial skills sync when `CLAUDE_CODE_SYNC_SKILLS` is set (default: 5000). When exceeded, the query proceeds and remaining skill downloads continue in the background |

| `CLAUDE_CODE_SYNTAX_HIGHLIGHT` | Set to `false` to disable syntax highlighting in diff output. Useful when colors interfere with your terminal setup. To also disable highlighting in code blocks and file previews, use the [`syntaxHighlightingDisabled`](/en/settings) setting |

@@ -288,6 +289,7 @@ Claude Code reads environment variables at startup, so changes take effect the n

| `DISABLE_LOGIN_COMMAND` | Set to `1` to hide the `/login` command. Useful when authentication is handled externally via API keys or `apiKeyHelper` |

| `DISABLE_LOGOUT_COMMAND` | Set to `1` to hide the `/logout` command |

| `DISABLE_PROMPT_CACHING` | Set to `1` to disable [prompt caching](/en/prompt-caching#disable-prompt-caching) for all models (takes precedence over per-model settings) |

| `DISABLE_PROMPT_CACHING_FABLE` | Set to `1` to disable prompt caching for Fable models |

| `DISABLE_PROMPT_CACHING_HAIKU` | Set to `1` to disable prompt caching for Haiku models |

| `DISABLE_PROMPT_CACHING_OPUS` | Set to `1` to disable prompt caching for Opus models |

| `DISABLE_PROMPT_CACHING_SONNET` | Set to `1` to disable prompt caching for Sonnet models |

@@ -340,6 +342,8 @@ Claude Code reads environment variables at startup, so changes take effect the n

| `VERTEX_REGION_CLAUDE_4_6_OPUS` | Override region for Claude Opus 4.6 when using Vertex AI |

| `VERTEX_REGION_CLAUDE_4_6_SONNET` | Override region for Claude Sonnet 4.6 when using Vertex AI |

| `VERTEX_REGION_CLAUDE_4_7_OPUS` | Override region for Claude Opus 4.7 when using Vertex AI. Added in v2.1.111 |

| `VERTEX_REGION_CLAUDE_4_8_OPUS` | Override region for Claude Opus 4.8 when using Vertex AI. Added in v2.1.154 |

| `VERTEX_REGION_CLAUDE_FABLE_5` | Override region for Claude Fable 5 when using Vertex AI. Added in v2.1.170 |

| `VERTEX_REGION_CLAUDE_HAIKU_4_5` | Override region for Claude Haiku 4.5 when using Vertex AI |

Standard OpenTelemetry exporter variables (`OTEL_METRICS_EXPORTER`, `OTEL_LOGS_EXPORTER`, `OTEL_EXPORTER_OTLP_ENDPOINT`, `OTEL_EXPORTER_OTLP_PROTOCOL`, `OTEL_EXPORTER_OTLP_HEADERS`, `OTEL_METRIC_EXPORT_INTERVAL`, `OTEL_RESOURCE_ATTRIBUTES`, and signal-specific variants) are also supported. See [Monitoring](/en/monitoring-usage) for configuration details.

errors+18-0

1Mコンテキスト利用時にクレジットが必要な場合のエラー内容と、モデル切り替えなどの対処方法が新設されました。

@@ -26,6 +26,7 @@ Match the message you see in your terminal to a section below.

| `Auto mode could not evaluate this action and is blocking it for safety` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |

| `Auto mode classifier transcript exceeded context window` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |

| `You've hit your session limit` / `You've hit your weekly limit` | [Usage limits](#you%E2%80%99ve-hit-your-session-limit) |

| `Usage credits required for 1M context` | [Usage limits](#usage-credits-required-for-1m-context) |

| `Server is temporarily limiting requests` | [Usage limits](#server-is-temporarily-limiting-requests) |

| `Request rejected (429)` | [Usage limits](#request-rejected-429) |

| `Credit balance is too low` | [Usage limits](#credit-balance-is-too-low) |

@@ -188,6 +189,23 @@ Claude Code blocks further requests until the reset time shown in the message.

To watch your remaining allowance before you hit the limit, add the `rate_limits` fields to a [custom status line](/en/statusline#rate-limit-usage), or in the Desktop app click the [usage ring](/en/desktop#check-usage) next to the model picker.

### Usage credits required for 1M context

The selected model uses the 1M-token extended context window, and your plan only includes it through usage credits.

```text

API Error: Usage credits required for 1M context · run /usage-credits to turn them on, or /model to switch to standard context

```

This is an entitlement check, not a quota exhaustion. It fires even when your session and weekly allowances have capacity remaining. See [Extended context](/en/model-config#extended-context) for which plans include 1M context directly and which require usage credits.

**What to do:**

- Run `/model` and select the variant without the `[1m]` suffix to fall back to the standard context window

- Run `/usage-credits` to turn on metered billing for the 1M variant on Pro and Max, or to request it from your admin on Team and Enterprise

- If the error persists after `/model`, a 1M model ID may be set elsewhere. See [There's an issue with the selected model](#there%E2%80%99s-an-issue-with-the-selected-model) for the configuration locations to check in priority order.

- To remove 1M variants from the model picker entirely, set [`CLAUDE_CODE_DISABLE_1M_CONTEXT=1`](/en/env-vars)

### Server is temporarily limiting requests

The API applied a short-lived throttle that is unrelated to your plan quota.

hooks-guide+1-1

ローカル設定ファイルが自動作成時のみgitignoreされるという詳細な仕様変更が反映されました。

@@ -717,7 +717,7 @@ Where you add a hook determines its scope:

| :- | :- | :- |

| `~/.claude/settings.json` | All your projects | No, local to your machine |

| `.claude/settings.json` | Single project | Yes, can be committed to the repo |

| `.claude/settings.local.json` | Single project | No, gitignored |

| `.claude/settings.local.json` | Single project | No, gitignored when Claude Code creates it |

| Managed policy settings | Organization-wide | Yes, admin-controlled |

| [Plugin](/en/plugins) `hooks/hooks.json` | When plugin is enabled | Yes, bundled with the plugin |

| [Skill](/en/skills) or [agent](/en/sub-agents) frontmatter | While the skill or agent is active | Yes, defined in the component file |

hooks+1-1

プロジェクト固有の設定ファイルのgit管理に関する説明が最新の仕様に合わせて微調整されました。

@@ -144,7 +144,7 @@ Where you define a hook determines its scope:

| :- | :- | :- |

| `~/.claude/settings.json` | All your projects | No, local to your machine |

| `.claude/settings.json` | Single project | Yes, can be committed to the repo |

| `.claude/settings.local.json` | Single project | No, gitignored |

| `.claude/settings.local.json` | Single project | No, gitignored when Claude Code creates it |

| Managed policy settings | Organization-wide | Yes, admin-controlled |

| [Plugin](/en/plugins) `hooks/hooks.json` | When plugin is enabled | Yes, bundled with the plugin |

| [Skill](/en/skills) or [agent](/en/sub-agents) frontmatter | While the component is active | Yes, defined in the component file |

large-codebases+1-1

手動で作成したsettings.local.jsonを自身でgitignoreに追加する必要があるという注意喚起が追加されました。

@@ -133,7 +133,7 @@ When you start Claude from the repository root, each subdirectory's CLAUDE.md lo

Use this for directories you never work in, such as other teams' packages, legacy code, or vendored subtrees. The exclusion list is static, not a per-task switch. To focus on one package today and another tomorrow, [start Claude from that package's directory](#choose-where-to-start-claude) instead of editing exclusions.

If you only want these exclusions for yourself, put the setting in `.claude/settings.local.json`, which is gitignored and not committed. Patterns use glob syntax matched against absolute file paths, so start relative-style patterns with `**/` to match anywhere in the tree. The example below excludes packages owned by other teams:

If you only want these exclusions for yourself, put the setting in `.claude/settings.local.json`. Claude Code gitignores that file when it creates it; since you're creating it by hand here, add it to your gitignore. Patterns use glob syntax matched against absolute file paths, so start relative-style patterns with `**/` to match anywhere in the tree. The example below excludes packages owned by other teams:

```json .claude/settings.local.json theme={null}

{

model-config+5-4

モデルエイリアスへのfableの追加と、特定のモデルセットにおけるプロンプトキャッシュ無効化の設定が記述されました。

@@ -399,9 +399,9 @@ Note: `ANTHROPIC_SMALL_FAST_MODEL` is deprecated in favor of

When deploying Claude Code through [Bedrock](/en/amazon-bedrock), [Vertex AI](/en/google-vertex-ai), [Foundry](/en/microsoft-foundry), or [Claude Platform on AWS](/en/claude-platform-on-aws), pin model versions before rolling out to users.

Without pinning, Claude Code uses model aliases such as `sonnet`, `opus`, and `haiku` that resolve to a built-in default model ID for each provider. That default can lag the newest Anthropic release, and the model it points to may not yet be enabled in a user's account. When the default is unavailable, Bedrock and Vertex AI users see a notice and fall back to the previous version for that session, while Foundry users see errors because Foundry has no equivalent startup check.

Without pinning, Claude Code uses model aliases such as `fable`, `opus`, `sonnet`, and `haiku` that resolve to a built-in default model ID for each provider. That default can lag the newest Anthropic release, and the model it points to may not yet be enabled in a user's account. When the default is unavailable, Bedrock and Vertex AI users see a notice and fall back to the previous version for that session, while Foundry users see errors because Foundry has no equivalent startup check.

Set all three model environment variables to specific version IDs as part of your initial setup. Pinning lets you control when your users move to a new model.

Set the model environment variables to specific version IDs as part of your initial setup. Pinning lets you control when your users move to a new model.

Use the following environment variables with version-specific model IDs for your provider:

@@ -411,7 +411,7 @@ Use the following environment variables with version-specific model IDs for your

| Vertex AI | `export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-8'` |

| Foundry | `export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-8'` |

Apply the same pattern for `ANTHROPIC_DEFAULT_SONNET_MODEL` and `ANTHROPIC_DEFAULT_HAIKU_MODEL`. For current and legacy model IDs across all providers, see [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview). To upgrade users to a new model version, update these environment variables and redeploy.

Apply the same pattern for `ANTHROPIC_DEFAULT_FABLE_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL`, and `ANTHROPIC_DEFAULT_HAIKU_MODEL`. For current and legacy model IDs across all providers, see [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview). To upgrade users to a new model version, update these environment variables and redeploy.

To enable [extended context](#extended-context) for a pinned model, append `[1m]` to the model ID in `ANTHROPIC_DEFAULT_OPUS_MODEL` or `ANTHROPIC_DEFAULT_SONNET_MODEL`:

@@ -425,7 +425,7 @@ The `[1m]` suffix applies the 1M context window to all usage of the `opus` and `

- Only append `[1m]` when the underlying model [supports 1M context](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window).

- The suffix is read per variable, not per model. On Bedrock, Vertex, and Foundry, a model ID without `[1m]` in one variable uses 200K context even if another variable sets the same model with the suffix.

The `settings.availableModels` allowlist still applies when using third-party providers. Filtering matches on the model alias (`opus`, `sonnet`, `haiku`), not the provider-specific model ID.

The `settings.availableModels` allowlist still applies when using third-party providers. Filtering matches on the model alias (`fable`, `opus`, `sonnet`, `haiku`), not the provider-specific model ID.

### Customize pinned model display and capabilities

@@ -499,5 +499,6 @@ Claude Code automatically uses [prompt caching](/en/prompt-caching) to optimize

| `DISABLE_PROMPT_CACHING_HAIKU` | Set to `1` to disable prompt caching for Haiku models only |

| `DISABLE_PROMPT_CACHING_SONNET` | Set to `1` to disable prompt caching for Sonnet models only |

| `DISABLE_PROMPT_CACHING_OPUS` | Set to `1` to disable prompt caching for Opus models only |

| `DISABLE_PROMPT_CACHING_FABLE` | Set to `1` to disable prompt caching for Fable models only |

To change the cache TTL or learn what triggers a cache miss, see [How Claude Code uses prompt caching](/en/prompt-caching).

monitoring-usage+1-1

メトリクス集計におけるモデル属性の利用範囲と、セッションIDを用いたデータ結合の必要性が説明されています。

@@ -1022,7 +1022,7 @@ Common alerts to consider:

- Unusual token consumption

- High session volume from specific users

All metrics can be segmented by `user.account_uuid`, `user.account_id`, `organization.id`, `session.id`, `model`, and `app.version`.

All metrics can be segmented by the [standard attributes](#standard-attributes). The `model` attribute is available on `claude_code.token.usage` and `claude_code.cost.usage` only; activity counters have never carried it. Per-model breakdowns of lines of code or commits can only be approximated by joining against the token or cost metrics on `session.id`, since one session can span multiple models.

### Detect retry exhaustion

overview+6-6

コードブロックのスタイル指定が修正され、テレポート機能の利用にはサブスクリプションが必要である旨が追記されました。

@@ -19,19 +19,19 @@ To install Claude Code, use one of the following methods:

**macOS, Linux, WSL:**

```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} 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} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}

curl -fsSL https://claude.ai/install.sh | bash

```

**Windows PowerShell:**

```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={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} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}

irm https://claude.ai/install.ps1 | iex

```

**Windows CMD:**

```batch theme={null}

```batch 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} 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} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}

curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd

```

@@ -41,7 +41,7 @@ If you see `The token '&&' is not a valid statement separator`, you're in PowerS

Native installations automatically update in the background to keep you on the latest version.

```bash theme={null}

brew install --cask claude-code

```

@@ -49,7 +49,7 @@ Homebrew offers two casks. `claude-code` tracks the stable release channel, whic

Homebrew installations do not auto-update. Run `brew upgrade claude-code` or `brew upgrade claude-code@latest`, depending on which cask you installed, to get the latest features and security fixes.

```powershell theme={null}

winget install Anthropic.ClaudeCode

```

@@ -160,7 +160,7 @@ Sessions aren't tied to a single surface. Move work between environments as your

- Step away from your desk and keep working from your phone or any browser with [Remote Control](/en/remote-control)

- Message [Dispatch](/en/desktop#sessions-from-dispatch) a task from your phone and open the Desktop session it creates

- Kick off a long-running task on the [web](/en/claude-code-on-the-web) or [iOS app](https://apps.apple.com/app/claude-by-anthropic/id6473753684), then pull it into your terminal with `claude --teleport`

- Hand off a terminal session to the [Desktop app](/en/desktop) with `/desktop` for visual diff review

- Route tasks from team chat: mention `@Claude` in [Slack](/en/slack) with a bug report and get a pull request back

permission-modes+2-0

設定ファイルによる事前承認が保護パスへの書き込み制限には適用されないという制限事項が明記されました。

@@ -298,6 +298,8 @@ Writes to a small set of paths are never auto-approved, in every mode except `by

| `dontAsk` | Denied |

| `bypassPermissions` | Allowed |

[`permissions.allow`](/en/permissions#manage-permissions) rules in settings files do not pre-approve protected-path writes. The safety check runs before Claude Code evaluates allow rules from settings, so an entry such as `Edit(.claude/**)` in `~/.claude/settings.json` or `.claude/settings.json` does not change the per-mode outcome in the table above. In modes that prompt, the prompt for a `.claude/` write offers **Yes, and allow Claude to edit its own settings for this session**, which approves later `.claude/` writes in that session without prompting again.

Protected directories:

- `.git`

permissions+1-1

権限ルールが「拒否、確認、許可」の順序で評価され、具体性よりもこの順序が優先される仕様が詳しく説明されています。

@@ -27,7 +27,7 @@ You can view and manage Claude Code's tool permissions with `/permissions`. This

- **Ask** rules prompt for confirmation whenever Claude Code tries to use the specified tool.

- **Deny** rules prevent Claude Code from using the specified tool.

Rules are evaluated in order: **deny -> ask -> allow**. The first matching rule wins, so deny rules always take precedence.

Rules are evaluated in order: deny, then ask, then allow. The first match in that order determines the outcome, and rule specificity does not change the order. A matching ask rule prompts even when a more specific allow rule also matches the same call.

Deny rules behave differently depending on whether they name a tool or scope a pattern within one. A bare tool name like `Bash` removes the tool from Claude's context entirely, so Claude never sees it. A scoped rule like `Bash(rm *)` leaves the tool available and blocks matching calls when Claude attempts them.

prompt-caching+1-0

Fableモデル限定でプロンプトキャッシュを無効化するための環境変数が追加されました。

@@ -227,6 +227,7 @@ Disabling caching is occasionally useful when debugging caching behavior with a

| `DISABLE_PROMPT_CACHING_HAIKU` | Disable for Haiku only |

| `DISABLE_PROMPT_CACHING_SONNET` | Disable for Sonnet only |

| `DISABLE_PROMPT_CACHING_OPUS` | Disable for Opus only |

| `DISABLE_PROMPT_CACHING_FABLE` | Disable for Fable only |

To set caching policy across an organization, put any of these or the [TTL variables](#cache-lifetime) in the `env` block of [managed settings](/en/settings#settings-files). For normal use, leave caching enabled.

remote-control+7-1

フッター部分へのアクティブインジケーター表示や、セッションURLおよびQRコードへのアクセス方法が更新されました。

@@ -68,6 +68,8 @@ claude --remote-control "My Project"

This gives you a full interactive session in your terminal that you can also control from claude.ai or the Claude app. Unlike `claude remote-control` (server mode), you can type messages locally while the session is also available remotely.

As of v2.1.162, a `Remote Control active` indicator stays in the footer below the input box while Remote Control is connected. The indicator text is a link to the session on claude.ai, so you can reopen it from the terminal at any time. Select the indicator with the down arrow key and press Enter to open a status panel with the session URL and a QR code.

If you're already in a Claude Code session and want to continue it remotely, use the `/remote-control` (or `/rc`) command:

```text theme={null}

@@ -80,7 +82,11 @@ Pass a name as an argument to set a custom session title:

/remote-control My Project

```

This starts a Remote Control session that carries over your current conversation history and displays a session URL and QR code you can use to [connect from another device](#connect-from-another-device). The `--verbose`, `--sandbox`, and `--no-sandbox` flags are not available with this command.

This starts a Remote Control session that carries over your current conversation history.

As of v2.1.162, a `Remote Control active` indicator appears in the footer below the input box and stays visible while the connection is up. The indicator text is a link to the session on claude.ai. Select it with the down arrow key and press Enter, or run `/remote-control` again, to open a status panel with the session URL and a QR code you can use to [connect from another device](#connect-from-another-device).

The `--verbose`, `--sandbox`, and `--no-sandbox` flags are not available with this command.

In the [Claude Code VS Code extension](/en/vs-code), type `/remote-control` or `/rc` in the prompt box, or open the command menu with `/` and select it. Requires Claude Code v2.1.79 or later.

sandboxing+6-4

サンドボックス環境におけるファイルアクセス権限や設定の適用範囲に関する説明が強化されました。

@@ -40,7 +40,7 @@ If the panel shows only a Dependencies tab, a required package is missing. Insta

On the Mode tab, select auto-allow or regular permissions. Auto-allow runs sandboxed commands without prompting, and regular permissions keeps the regular permission prompts even when commands are sandboxed. See [Sandbox modes](#sandbox-modes) for which commands still prompt in auto-allow mode.

Ask Claude to run a command, such as a build or a test suite. By default, commands inside the sandbox can write only to the working directory. The first time a command needs a new network domain, Claude Code prompts for approval.

Ask Claude to run a command, such as a build or a test suite. By default, commands inside the sandbox can write only to the working directory and the session temp directory. The first time a command needs a new network domain, Claude Code prompts for approval.

Commands that cannot run sandboxed fall back to the regular permission flow. To widen or narrow these boundaries, see [Configure sandboxing](#configure-sandboxing).

@@ -112,6 +112,8 @@ Even in auto-allow mode, the following still apply:

In both modes, the sandbox enforces the same filesystem and network restrictions. The difference is only in whether sandboxed commands are auto-approved or require explicit permission.

The session temp directory is writable inside the sandbox by default, alongside the working directory. Claude Code sets `$TMPDIR` to this directory for sandboxed commands, so tools that write temporary files work without extra configuration. Unsandboxed commands inherit your shell's `$TMPDIR` unchanged, which means sandboxed and unsandboxed commands resolve `$TMPDIR` to different directories. To pass temporary files between the two, write them under the working directory instead.

Some commands cannot run inside the sandbox at all, such as tools that are incompatible with it or that need a host you have not allowed. Rather than failing the task or requiring you to turn sandboxing off, Claude Code includes an escape hatch: when a command fails because of sandbox restrictions, Claude analyzes the failure and may retry the command with the `dangerouslyDisableSandbox` parameter. The retried command runs outside the sandbox, so it goes through the regular permission flow and requires your approval.

You can disable this escape hatch by setting `"allowUnsandboxedCommands": false` in your [sandbox settings](/en/settings#sandbox-settings). When disabled, which the `/sandbox` Overrides tab shows as **Strict sandbox mode**, the `dangerouslyDisableSandbox` parameter is completely ignored and all commands must run sandboxed or be explicitly listed in `excludedCommands`.

@@ -122,7 +124,7 @@ Auto-allow mode works independently of your permission mode setting. Even if you

Customize sandbox behavior through your `settings.json` file. See [Settings](/en/settings#sandbox-settings) for the complete configuration reference.

By default, sandboxed commands can only write to the current working directory. If subprocess commands like `kubectl`, `terraform`, or `npm` need to write outside the project directory, use `sandbox.filesystem.allowWrite` to grant access to specific paths:

By default, sandboxed commands can write only to the current working directory and the session temp directory. If subprocess commands like `kubectl`, `terraform`, or `npm` need to write outside those directories, use `sandbox.filesystem.allowWrite` to grant access to specific paths:

```json

{

@@ -173,9 +175,9 @@ The `.` in `allowRead` resolves to the project root because this configuration l

The sandboxed Bash tool restricts file system access to specific directories:

- **Default write behavior**: read and write access to the current working directory and its subdirectories

- **Default write behavior**: read and write access to the current working directory and its subdirectories, plus the session temp directory that `$TMPDIR` points to

- **Default read behavior**: read access to the entire computer, except certain denied directories. Note that this default still allows reading credential files such as `~/.aws/credentials` and `~/.ssh/`. Add them to `denyRead` to block them.

- **Blocked access**: cannot modify files outside the current working directory without explicit permission, including shell configuration files such as `~/.bashrc` and system binaries in `/bin/`

- **Blocked access**: cannot modify files outside the current working directory and session temp directory without explicit permission, including shell configuration files such as `~/.bashrc` and system binaries in `/bin/`

- **Git worktrees**: when the working directory is a [linked git worktree](/en/worktrees), the sandbox also allows writes to the main repository's shared `.git` directory so commands such as `git commit` can update refs and the index. Writes to `hooks/` and `config` inside that directory remain denied.

- **Configurable**: define custom allowed and denied paths through settings

settings+6-5

設定ファイルのスコープや、特定の動作モードにおける優先順位の定義が整理されました。

@@ -20,7 +20,7 @@ Claude Code uses a **scope system** to determine where configurations apply and

### When to use each scope

@@ -85,7 +85,7 @@ Code through hierarchical settings:

projects.

- **Project settings** are saved in your project directory:

- `.claude/settings.json` for settings that are checked into source control and shared with your team

- `.claude/settings.local.json` for settings that are not checked in, useful for personal preferences and experimentation. Claude Code will configure git to ignore `.claude/settings.local.json` when it is created.

- `.claude/settings.local.json` for settings that are not checked in, useful for personal preferences and experimentation. When Claude Code creates `.claude/settings.local.json`, it configures git to ignore the file. If you create the file yourself, add it to your gitignore manually.

- **Managed settings**: For organizations that need centralized control, Claude Code supports multiple delivery mechanisms for managed settings. All use the same JSON format and cannot be overridden by user or project settings:

- **Server-managed settings**: delivered from Anthropic's servers via the Claude.ai admin console. See [server-managed settings](/en/server-managed-settings).

@@ -327,7 +327,7 @@ To copy gitignored files like `.env` into new worktrees, use a [`.worktreeinclud

### Permission rule syntax

Permission rules follow the format `Tool` or `Tool(specifier)`. Rules are evaluated in order: deny rules first, then ask, then allow. The first matching rule wins.

Permission rules follow the format `Tool` or `Tool(specifier)`. Rules are evaluated in order: deny rules first, then ask, then allow. The first match determines the outcome regardless of rule specificity. See the [permission rule evaluation order](/en/permissions#manage-permissions) for details.

Quick examples:

@@ -482,6 +482,7 @@ src/components/Form.tsx

```bash

#!/bin/bash

query=$(cat | jq -r '.query')

# Replace your-repo-file-index with your own file search command

your-repo-file-index --query "$query" | head -20

```

@@ -573,7 +574,7 @@ For example, if your user settings set `permissions.defaultMode` to `acceptEdits

Run `/status` inside Claude Code to see which settings sources are active. The Status tab includes a `Setting sources` line that lists each layer Claude Code loaded for the current session, such as `User settings` or `Project local settings`. When [managed settings](/en/admin-setup#decide-how-settings-reach-devices) are in effect, the entry shows the delivery channel in parentheses, for example `Enterprise managed settings (remote)`, `(plist)`, `(HKLM)`, `(HKCU)`, or `(file)`. A layer appears in the list only when that source is loaded with at least one key, so an empty list means no settings sources were found.

The `Setting sources` line confirms which sources are being read. It does not show which layer supplied each individual key. The Config tab in the same dialog is an editor for a fixed set of toggles such as theme and verbose output, not a view of your `settings.json` contents. If a settings file contains errors, such as invalid JSON or a value that fails validation, `/status` reports the issue so you can fix it.

### Key points about the configuration system

@@ -651,7 +652,7 @@ Controls which plugins are enabled. Format: `"plugin-name@marketplace-name": tru

- **User settings** (`~/.claude/settings.json`): Personal plugin preferences

- **Project settings** (`.claude/settings.json`): Project-specific plugins shared with team

- **Local settings** (`.claude/settings.local.json`): Per-machine overrides (not committed)

- **Local settings** (`.claude/settings.local.json`): Per-machine overrides, gitignored when Claude Code creates it

- **Managed settings** (`managed-settings.json`): Organization-wide policy overrides that block installation at all scopes and hide the plugin from the marketplace

Project settings take precedence over user settings, so setting a plugin to `false` in `~/.claude/settings.json` does not disable a plugin that the project's `.claude/settings.json` enables. To opt out of a project-enabled plugin on your machine, set it to `false` in `.claude/settings.local.json` instead.

setup+29-9

インストール時のトラブルシューティングや、特定のOS環境でのセットアップ手順が詳しく拡充されました。

@@ -38,19 +38,19 @@ To install Claude Code, use one of the following methods:

**macOS, Linux, WSL:**

```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}

curl -fsSL https://claude.ai/install.sh | bash

```

**Windows PowerShell:**

```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={null}

irm https://claude.ai/install.ps1 | iex

```

**Windows CMD:**

```batch 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}

curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd

```

@@ -60,7 +60,7 @@ If you see `The token '&&' is not a valid statement separator`, you're in PowerS

Native installations automatically update in the background to keep you on the latest version.

```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}

brew install --cask claude-code

```

@@ -68,7 +68,7 @@ Homebrew offers two casks. `claude-code` tracks the stable release channel, whic

Homebrew installations do not auto-update. Run `brew upgrade claude-code` or `brew upgrade claude-code@latest`, depending on which cask you installed, to get the latest features and security fixes.

```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={null}

winget install Anthropic.ClaudeCode

```

@@ -295,11 +295,11 @@ curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd 2.1.89 &&

### Install with Linux package managers

Claude Code publishes signed apt, dnf, and apk repositories. Replace `stable` with `latest` for the rolling channel. Package manager installations do not auto-update through Claude Code; updates arrive through your normal system upgrade workflow.

Claude Code publishes signed apt, dnf, and apk repositories. Each repository offers two channels: `stable` serves a version that is typically about one week old, skipping releases with major regressions, and `latest` serves every release as soon as it ships. The commands below configure the `stable` channel, which fits most users; each tab also shows the `latest` repository URL. Package manager installations do not auto-update through Claude Code; updates arrive through your normal system upgrade workflow.

All repositories are signed with the [Claude Code release signing key](#binary-integrity-and-code-signing). Before trusting the key, verify it as described in each tab.

For Debian and Ubuntu. To use the rolling channel, change both `stable` occurrences in the `deb` line: the URL path and the suite name.

For Debian and Ubuntu. The following commands configure the `stable` channel:

```bash theme={null}

sudo install -d -m 0755 /etc/apt/keyrings

@@ -311,11 +311,18 @@ sudo apt update

sudo apt install claude-code

```

To use the `latest` channel instead, both the URL path and the suite name change. Use this `deb` line:

```bash theme={null}

echo "deb [signed-by=/etc/apt/keyrings/claude-code.asc] https://downloads.claude.ai/claude-code/apt/latest latest main" \

| sudo tee /etc/apt/sources.list.d/claude-code.list

```

Verify the GPG key fingerprint before trusting it: `gpg --show-keys /etc/apt/keyrings/claude-code.asc` should report `31DD DE24 DDFA B679 F42D 7BD2 BAA9 29FF 1A7E CACE`.

To upgrade later, run `sudo apt update && sudo apt upgrade claude-code`.

For Fedora and RHEL:

For Fedora and RHEL. The following commands configure the `stable` channel:

```bash theme={null}

sudo tee /etc/yum.repos.d/claude-code.repo <<'EOF'

@@ -329,11 +336,17 @@ EOF

sudo dnf install claude-code

```

To use the `latest` channel instead, set `baseurl` to the `latest` repository:

```ini theme={null}

baseurl=https://downloads.claude.ai/claude-code/rpm/latest

```

dnf downloads the key on first install and prompts you to confirm the fingerprint. Verify it matches `31DD DE24 DDFA B679 F42D 7BD2 BAA9 29FF 1A7E CACE` before accepting.

To upgrade later, run `sudo dnf upgrade claude-code`.

For Alpine Linux:

For Alpine Linux. The following commands configure the `stable` channel:

```sh theme={null}

wget -O /etc/apk/keys/claude-code.rsa.pub \

@@ -342,6 +355,13 @@ echo "https://downloads.claude.ai/claude-code/apk/stable" >> /etc/apk/repositori

apk add claude-code

```

To switch to the `latest` channel, remove the `stable` repository line and add the `latest` repository:

```sh theme={null}

sed -i '\|downloads.claude.ai/claude-code/apk/stable|d' /etc/apk/repositories

echo "https://downloads.claude.ai/claude-code/apk/latest" >> /etc/apk/repositories

```

Verify the downloaded key with `sha256sum /etc/apk/keys/claude-code.rsa.pub`, which should report `395759c1f7449ef4cdef305a42e820f3c766d6090d142634ebdb049f113168b6`.

To upgrade later, run `apk update && apk upgrade claude-code`.

third-party-integrations+1-1

外部連携時の設定ファイル管理に関する記述が最新の共通仕様に合わせて更新されました。

@@ -308,7 +308,7 @@ Encourage new users to try Claude Code for codebase Q\&A, or on smaller bug fixe

### Pin model versions for cloud providers

If you deploy through [Bedrock](/en/amazon-bedrock), [Vertex AI](/en/google-vertex-ai), [Foundry](/en/microsoft-foundry), or [Claude Platform on AWS](/en/claude-platform-on-aws), pin specific model versions using `ANTHROPIC_DEFAULT_OPUS_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL`, and `ANTHROPIC_DEFAULT_HAIKU_MODEL`. Without pinning, model aliases resolve to Claude Code's built-in default for that provider, which can lag the newest release and may not yet be enabled in your account. Pinning lets you control when your users move to a new model. See [Model configuration](/en/model-config#pin-models-for-third-party-deployments) for what each provider does when the default is unavailable.

If you deploy through [Bedrock](/en/amazon-bedrock), [Vertex AI](/en/google-vertex-ai), [Foundry](/en/microsoft-foundry), or [Claude Platform on AWS](/en/claude-platform-on-aws), pin specific model versions using `ANTHROPIC_DEFAULT_FABLE_MODEL`, `ANTHROPIC_DEFAULT_OPUS_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL`, and `ANTHROPIC_DEFAULT_HAIKU_MODEL`. Without pinning, model aliases resolve to Claude Code's built-in default for that provider, which can lag the newest release and may not yet be enabled in your account. Pinning lets you control when your users move to a new model. See [Model configuration](/en/model-config#pin-models-for-third-party-deployments) for what each provider does when the default is unavailable.

### Configure security policies

troubleshoot-install+2-0

インストール失敗時の確認事項として、Node.jsのバージョン確認などの項目が追加されました。

@@ -163,6 +163,8 @@ Check the three locations a `claude` binary can come from. `~/.local/bin/claude`

ls -la ~/.local/bin/claude

```

If either `ls` command prints `No such file or directory`, that's not an error. It means nothing is installed at that location, so move on to the next check.

```bash theme={null}

ls -la ~/.claude/local/

```

worktrees+2-0

Git worktree環境における設定ファイルの共有と分離に関する挙動が補足されました。

@@ -91,6 +91,8 @@ When you exit a worktree session, cleanup depends on whether you made changes:

Worktrees that Claude created for subagents and [background sessions](/en/agent-view#how-file-edits-are-isolated) are removed automatically once they are older than your [`cleanupPeriodDays`](/en/settings#available-settings) setting, provided they have no uncommitted changes, no untracked files, and no unpushed commits. Worktrees you create with `--worktree` are never removed by this sweep.

While an agent is running, Claude runs `git worktree lock` on its worktree so that concurrent cleanup cannot remove it. The lock is released when the agent finishes. To clean up a worktree that the sweep keeps, run `git worktree remove`, adding `--force` if the worktree has uncommitted changes or untracked files.

## Manage worktrees manually

For full control over worktree location and branch configuration, create worktrees with Git directly. This is useful when you need to check out a specific existing branch or place the worktree outside the repository.