--- title: "Claude Code v2.1.207 Released: Auto Mode Enabled by Default, Major Bug Fixes and Security Improvements" source: "Claude Code：GitHub Releases（RSS）" source_tier: "t1_5" url: "https://github.com/anthropics/claude-code/releases/tag/v2.1.207" permalink: "https://feed.astralor.com/items/itm_c3736098cbeb1f592efc07ac" published: "2026-07-11T00:52:10.000Z" score: 81 channel: "ai" tags: ["Anthropic","Claude Code","Streaming","Stability and Security Fixes","Auto Mode"] --- # Claude Code v2.1.207 Released: Auto Mode Enabled by Default, Major Bug Fixes and Security Improvements ## AI commentary > The sheer length and depth of this fix list impress me—it covers nearly all common pain points, especially streaming stutter and remote security settings. If you use Claude Code daily, I highly recommend upgrading immediately for a noticeably smoother experience. ## At a glance Claude Code v2.1.207 is now available, with Auto mode enabled by default on Bedrock, Vertex AI, and Foundry (opt-in no longer required, can be disabled in settings). This release addresses numerous critical issues including terminal freezing during streaming of large content, overwriting of custom launcher scripts, remote managed settings consent, prompt-injection warnings, compound command permissions, transcript scrolling artifacts, Git config residue, malformed bracket patterns causing read failures, agent team crash loops, background session resumption, remote control task updates, deep research hostname labels, and AWS SSO credential requests. The default model is now Claude Opus 4.8, Auto mode settings have moved to user-level config, and plugin shell injection protections are strengthened. Overall stability, security, and user experience are significantly improved. ## Key points - Auto mode is now enabled by default without needing an environment variable; can be disabled in settings - Fixed terminal freezing and keystroke lag when streaming large tables, code blocks, and paragraphs - Comprehensive fixes for remote management consent, plugin shell injection, background sessions, git worktrees, and more - Default model changed to Claude Opus 4.8; Auto mode settings moved to user-level config ## Full text What's changed Auto mode is now available without CLAUDE_CODE_ENABLE_AUTO_MODE opt-in on Bedrock, Vertex AI, and Foundry; disable via disableAutoMode in settings Fixed the terminal freezing and keystrokes lagging while streaming responses containing very long lists, tables, paragraphs, or code blocks Fixed remote managed settings from a non-interactive run (claude -p, the SDK) being permanently recorded as consented without ever showing the security consent dialog Fixed spurious prompt-injection warnings triggered by benign system-generated conversation updates Fixed the auto-updater overwriting a custom launcher script or symlink at ~/.local/bin/claude on every release; /doctor now reports an externally managed launcher Fixed compound commands with cd prompting for permission when the only output redirect was to /dev/null Fixed the transcript jumping above the start of the answer when a response finishes streaming Fixed extensions.worktreeConfig being left in the repo's .git/config (breaking go-git tools like tea) after the last worktree.sparsePaths worktree was removed Fixed malformed bracket patterns in rules globs, skill paths, .ignore, and .worktreeinclude breaking file reads, file suggestions, and worktree creation Fixed a crash loop in agent teams where a malformed teammate mailbox message caused repeated errors every second until the mailbox file was manually deleted Fixed background sessions auto-named by accepting a plan not showing that name on their agent-view row Fixed background sessions that entered a git worktree resuming blank after a cold reopen from the agent list Fixed Remote Control task status updates being lost when the connection recovered from a network interruption or credential refresh Fixed Remote Control sessions hosted by the desktop app not showing background agent and workflow progress on mobile and web Fixed Deep research runs labeling every Fetch-phase agent "unknown" — chips now show the source hostname Fixed Bedrock repeatedly requesting fresh AWS SSO credentials from IAM Identity Center on every API request Improved agent view: pasting the same text again now expands the collapsed [Pasted text #N] placeholder instead of adding a second one Improved agent view: blocked session peeks now lead with the question and show a worded staleness clock (waiting 3m) instead of the same timestamp twice Changed Bedrock, Vertex, and Claude Platform on AWS to default to Claude Opus 4.8 Changed auto mode to no longer read autoMode from .claude/settings.local.json (repo-resident); use ~/.claude/settings.json instead Fixed an indefinite hang on Windows when AWS credential resolution stalls (e.g. a stuck credential_process): the 60-second stall guard now fires instead of waiting forever. Plugin hooks/monitors/MCP headersHelper: ${user_config.*} in shell-form commands is now rejected (shell-injection fix). Hooks: use exec form (args array) or $CLAUDE_PLUGIN_OPTION_; monitors and headersHelper: read the value inside the script (config file or the server's env block). Plugin option values (pluginConfigs) are no longer read from project-level .claude/settings.json; only user, --settings, and managed settings are honored Fixed /usage-credits amount inputs silently stripping malformed values (e.g. a pasted timestamp) to digits; malformed amounts are now rejected with an error, and amounts over $1,000 require a typed confirmation --- Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_c3736098cbeb1f592efc07ac