2.1.208
Claude Code 2.1.208 - リリースノート
2026年7月14日
Claude Code
日本語サマリー
Claude Code 2.1.208 リリースノート要約
[注意] セキュリティ・破壊的挙動の修正
- 危険なコマンドの実行防止:
--dangerously-skip-permissionsモードや auto モードにおいて、コマンド内の$(…)、バックティック、<(…)を含む致命的な削除(例:rm -rf ~)が実行される際に、確認プロンプトを表示するよう修正されました。- 権限・認証エラーの早期発見:
apiKeyHelperのスクリプトエラーが隠蔽される問題(無言のリトライ後に汎用401エラーになる)が修正され、3回以内にエラーが表示されるようになりました。
主な変更点・新機能
- スクリーンリーダーモード: アクセシビリティ向上のため、プレーンテキストレンダリングのスクリーンリーダーモード(
claude --ax-screen-readerなど)を追加。 - Vimモード拡張:
vimInsertModeRemaps設定を追加し、jjなどの2ストロークキーを Escape に割り当て可能に。 - コーポレートランチャー対応: すべての Claude Code 自己起動において、指定のラッパー実行ファイルを経由する
CLAUDE_CODE_PROCESS_WRAPPERを追加。 - UI/操作改善: マルチセレクトメニューやフルスクリーンモードでのマウスクリックをサポート。また、バックグラウンドエージェントのタスク進捗やUI再レンダリングの最適化により入力応答性が向上。
パフォーマンス・メモリ改善
- メモリ使用量の削減: ロングセッションでの複数のメモリリークを修正(MCP stderrの蓄積、LSPドキュメントの無制限オープン、画像データの保持など)。ファイル編集キャッシュを16 MB に制限。
- CPUオーバーヘッドの削減: ツール呼び出し時のCPU負荷を大幅に削減し(最大7倍高速化)、多くの権限ルールがあるセッションでの動作遅延を解消。
- ディスク/トランスクリプトの最適化: セッションのトランスクリプトサイズを最大79倍に圧縮し、チェックポイントのディスク使用量を制限。
主なバグ修正
- fast mode: モデル切り替え後に fast mode がオフになり、設定が復元されない問題を修正。
- 背景セッション: エージェントへの返信喪失や、アップデート後のデーモン起動失敗("Couldn't start the background daemon")、HTTP/2 GOAWAY によるクラッシュを修正。
- コンテキストウィンドウ誤表示: CLI自動更新後、一時的に200kにリセットされ「100% context used」と誤表示される問題を修正。
- トークン/出力関連:
CLAUDE_CODE_MAX_OUTPUT_TOKENS環境変数で指数表記(1e6など)の仮数だけが使われるバグ、claude -pの大規模出力切捨てを修正。 - ツール類の安定性: 巨大なMarkdownテーブルや、非常に長い1行を持つファイルの読み込み時のメモリ膨張・フリーズを修正。
Edit、Read、Grep、Glob各ツールの予期せぬエラーやクラッシュを修正。 - Bedrock連携: AWS SSO環境での認証エラーや、プロキシ変換時の誤解を招くストリーミングエラーを修正。
原文(Release Notes)
What's changed
- Added screen reader mode: opt-in plain-text rendering for screen reader users. Run
claude --ax-screen-reader, set CLAUDE_AX_SCREEN_READER=1, or add "axScreenReader": true to settings.- Added
vimInsertModeRemapssetting: map two-key insert-mode sequences likejjto Escape in vim mode- Added
CLAUDE_CODE_PROCESS_WRAPPER: agent view and the background service now honor a corporate launcher by running every Claude Code self-spawn through a required wrapper executable- Added mouse-click support for multi-select menus and "Other" input rows in fullscreen mode
- Fixed fast mode staying off after switching back to a model that supports it — it now restores automatically when enabled in settings
- Fixed replies typed to a background agent being lost when delivery fails — the text is now saved and delivered when the session restarts
- Fixed background-session attach failing permanently ("Couldn't start the background daemon") after an update replaced the binary a running
claude agentsprocess was launched from- Fixed the context window (and auto-compact indicator) briefly resetting to 200k after the CLI auto-updates, causing a false "100% context used" when resuming long-context sessions
- Fixed supervised and background sessions crashing when a server closed an HTTP/2 connection with a GOAWAY while requests were in flight
- Fixed truncated stream-json/JSON output and missing result message when piping large responses from
claude -p- Fixed
CLAUDE_CODE_MAX_OUTPUT_TOKENSand similar env vars silently using the mantissa of scientific-notation values (1e6became1)- Fixed very large markdown tables stalling rendering or using excessive memory; tables over 200 rows show the first 200 with a "… N more rows" notice
- Fixed the Edit tool failing on files modified after reading when the target text still matches uniquely
- Fixed Read reporting empty files as "shorter than offset", Grep silently returning "No files found" for invalid regex patterns, Grep count mode under-reporting totals when paginated, and Glob crashing with an unclear error when the pattern, path, or working directory contained a null byte
- Fixed
apiKeyHelperscript failures being hidden behind a generic 401 after ~10 silent retries; the script's own error is now shown within 3 attempts- Fixed Bedrock streaming requests failing with a misleading "Truncated event message received" when a gateway transforms the response — the error now names the content-type and points at the proxy
- Fixed
/upgradeshowing a login flow instead of the upgrade URL when the browser fails to open- Fixed stream-json input killing the session on blank CRLF or whitespace-only lines from Windows-style SDK hosts
- Fixed headless stream-json sessions hanging permanently when a
control_requestcarried a non-stringset_modelpayload; the CLI now answers with an error response- Fixed repeated "No completion record was found" notices on session resume — orphaned background tasks now collapse into a single summary
- Fixed Remote Control clients attaching to a terminal-hosted session not seeing background agents and workflow progress until a task started or stopped
- Fixed the Agent tool launching with no tools when a subagent's
toolslist resolves to nothing — it now returns a clear error naming the unrecognized entries- Fixed
/usageshowing stale cached bars over fresher data, and/mcpnot reclassifying placeholder servers after config edits- Fixed "Change directory" in SDK hosts (e.g. Claude Desktop) failing with "A turn is in progress" on idle sessions that have a running background task
- Fixed the workflow save dialog showing
~/.claude/workflows/instead of theCLAUDE_CONFIG_DIRlocation for user-scope saves- Fixed
/release-notesadding the viewed notes to the model's context — "Show all" previously injected the entire changelog into every subsequent request- Fixed a memory leak in the agent view where pasted images were retained for the screen's lifetime after sending peek replies
- Fixed SDK sessions losing agents defined via the initialize request when a plugin refresh ran before the client attached
- Fixed several memory leaks in long sessions: MCP stdio server stderr accumulating up to 64 MB per server, LSP documents staying open indefinitely (now LRU with 50-doc cap), async hook output retained after backgrounding, and unbounded growth in headless/SDK sessions from large tool-result payloads
- Fixed a memory blowup when reading files with extremely long single lines using offset/limit — the read now returns a clean error instead of loading the whole line
- Fixed multi-second per-turn slowdowns in sessions with many permission deny/ask rules — rule matchers are now compiled once and cached
- Improved input responsiveness while agent task lists update — task updates no longer re-render the entire UI
- Reduced per-tool-call CPU overhead in print/SDK sessions with many MCP tools by caching tool-pool assembly (up to 7x faster tool rounds at high tool counts)
- Reduced memory usage by bounding the file edit read cache to 16 MB instead of pinning up to 1,000 full files
- Reduced session transcript size (up to 79x in edit-heavy sessions) and bounded checkpoint disk usage by pruning superseded file-history backups
- Reduced memory usage when resuming sessions with background agents or forks spawned from large conversations
- Completed background agents now stay listed in
/tasksuntil cleanup instead of vanishing the moment they finish- Attaching to a stopped background agent now shows its transcript immediately while the session warms up, instead of a blank "Session is starting" screen
- Background sessions: an older daemon no longer silently restarts workers spawned by a newer version onto the older binary
- Agent view: Ctrl+X now deletes renamed-branch worktrees, never destroys unpushed commits, keeps the session row when a worktree is kept, and reused worktree names reset to the current base
- Catastrophic removals (e.g.
rm -rf ~) in commands containing$(…)/backticks/<(…)now prompt in--dangerously-skip-permissionsand auto mode, matching the plain form/install-github-appand the/mcpsettings menu no longer open in background sessions- MCP servers configured with an empty URL now show as "not configured" in
/mcpinstead of a config error/usagenow shows your last-known usage bars with an "as of" note when the usage endpoint is rate-limited, instead of an error screen- Fixed Bedrock auth failing with "Session token not found or invalid" for AWS SSO profiles whose sso_region differs from the Bedrock region (2.1.207 regression)