Claude Code Releases

Claude's `/verify` and `/code-review` skills now require explicit invocation.

• Claude will no longer automatically run `/verify` and `/code-review`.
• Users must now use the slash commands `/verify` or `/code-review` to trigger these skills.

This update focuses on enhancing security and stability by fixing numerous permission-related bugs in Bash and PowerShell, improving tool handling, and addressing issues with background sessions and OpenTelemetry logging.

• Numerous permission check vulnerabilities and misbehaviors in Bash and PowerShell have been fixed to prevent unintended command execution and ensure proper user prompts.
• Stability improvements include fixes for tool execution, memory management, background session handling, and streaming output, especially in corporate proxy environments.

Claude Code version 2.1.212 introduces enhanced background session management, new auto-mode reset functionality, and robust limits on tool calls and subagent spawns to prevent runaway processes, alongside numerous bug fixes for stability and user experience.

• New `/fork` command creates a background session for conversations.
• Added `claude auto-mode reset` to revert to default auto-mode settings.
• Implemented session-wide limits for WebSearch tool calls and subagent spawns.
• Long-running MCP tool calls are now automatically moved to the background.
• Fixed several issues related to plan mode execution, file handling, tool failures, and background session management on Windows.

This changelog for Claude Code 2.1.211 details new features like including subagent text in JSON output, numerous bug fixes across various functionalities including permissions, auto mode, session management, file uploads, and UI elements, performance improvements for terminal rendering and background agent reporting, and updates to environment variable parsing, documentation links, and permission rule saving.

• New `--forward-subagent-text` flag and `CLAUDE_CODE_FORWARD_SUBAGENT_TEXT` environment variable for streaming subagent output.
• Extensive bug fixes addressing issues with permissions, auto mode, session synchronization, file uploads, UI delays, and background job handling.
• Performance enhancements in terminal rendering and background agent result reporting.
• Updates to how integer environment variables are parsed, documentation links, and the persistence of permission rules.

This release includes 2 new features and 18 bug fixes.

• Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck
• Added a startup warning for `Write(path)`, `NotebookEdit(path)`, and `Glob(path)` permission rules — use `Edit(path)` or `Read(path)` instead
• Fixed `isolation: 'worktree'` subagents being able to run git-mutating commands against the main repo checkout instead of their own isolated worktree
• Fixed the `ultracode` keyword opt-in firing on non-human-originated input such as webhook payloads and relayed PR comments
• Fixed a rendered text fragment leaking into crash telemetry when a UI component returned content outside a styled text element
• Fixed paste markers leaking into external editors opened from Claude Code, which could appear as stray È/É characters around pasted text
• Fixed `claude attach` sometimes failing with "job not found" or "agent is still starting" errors during session transitions — attach now waits for the daemon to settle, and terminal resizes during a slow attach are applied once it completes
• Fixed a session crash when a tool's result renderer returned a numeric bigint value or plain text instead of a UI element
• Fixed a hook callback timeout being misreported to the model as a user rejection, which made unattended sessions stop and wait
• Fixed Claude assuming a `cd` took effect after its command was moved to the background; the tool result now states the working directory is unchanged
• Fixed plugin-provided MCP servers being torn down when MCP servers are re-synced mid-session
• Fixed plan approvals without edits being labeled "(edited by user)" and overwriting the plan file with a stale snapshot
• Fixed `/doctor` skipping its auto-mode-default proposal on Bedrock, Vertex, and Foundry, where auto mode no longer needs an opt-in
• Fixed Grep content mode claiming "No matches found" when paginating past the end of results

This release fixes an issue where dialogs in background sessions of `claude agents` were blocked.

• Dialogs in background sessions of `claude agents` are no longer blocked.

This release introduces auto mode without opt-in, numerous bug fixes for terminal performance, remote settings, prompt injections, and various agent and plugin functionalities, alongside model and configuration updates.

• Auto mode is now generally available across platforms, simplifying its usage.
• Significant fixes address terminal responsiveness, remote settings consent, prompt injection warnings, and plugin security.
• Default model for Bedrock, Vertex AI, and Claude Platform on AWS is updated to Claude Opus 4.8.
• Configuration settings for auto mode and plugin options have been adjusted for clarity and security.

This release introduces new features like directory path suggestions and a `/doctor` check for CLAUDE.md files, improves background agent handling, and fixes numerous bugs across various functionalities including login, model picking, and agent management.

• Directory path suggestions added to `/cd`.
• New `/doctor` check to trim `CLAUDE.md` files.
• Background agents now upgrade more efficiently.
• Resolved various bugs related to login, model selection, keyboard input, and agent lifecycle management.

Version 2.1.205 introduces auto mode enhancements, bug fixes across various features including session management and agent handling, and improvements to the agent view and update process.

• Auto mode is improved to ask before running potentially destructive commands and to block tampering with session transcript files.
• Significant bug fixes address issues with JSON schema generation, message handling, file operations on Windows, agent status display, and session-to-PR linking.

Fixed an issue where hook events were not streaming during SessionStart hooks in headless sessions, preventing remote workers from being idly reaped.

• Hook events now stream correctly during SessionStart in headless sessions.
• Resolved the problem of remote workers being idly reaped mid-hook.

This release includes 2 new features, 13 bug fixes, and 3 improvements.

• Added a "Dynamic workflow size" setting in `/config` for controlling how large Claude generally makes dynamic workflows (small/medium/large agent counts) — an advisory guideline, not an enforced cap
• Added `workflow.run_id` and `workflow.name` OpenTelemetry attributes to telemetry emitted by workflow-spawned agents, so a workflow run's activity can be reconstructed from OTel data
• Fixed a crash in the inline Ctrl+R history search when accepting or cancelling while the search was still scanning the history file
• Fixed `/rename` on background sessions being reverted when the job restarts, which broke addressing the session by its new name
• Fixed transient mTLS handshake failures when settings were re-applied during an in-place client certificate rotation
• Fixed commands sent from Remote Control (mobile/web) into an interactive session failing with "Unknown command"
• Fixed images and files sent from the Remote Control mobile or web app without a caption being silently dropped
• Fixed the sign-in URL printed by `claude auth login` and `claude mcp login --no-browser` not being reliably clickable when it wraps over SSH — it is now emitted as a single hyperlink
• Fixed opening a chat from `claude agents` sometimes failing with "currently running as a background agent" followed by a worker crash/respawn loop
• Fixed workflow scripts with unicode quote escapes in strings being corrupted before parsing; workflow parse errors now show the offending line instead of always blaming TypeScript
• Fixed voice dictation retrying in an unbounded loop when the microphone or audio recorder fails — repeated capture failures now pause voice input
• Fixed `/remote-control` sessions showing the wrong permission mode in the mobile and web apps
• Fixed resuming a session by name, or opening the resume picker, taking minutes and using a large amount of memory in repositories with many git worktrees

Claude Sonnet 5 sessions no longer use the mid-conversation system role for harness reminders

• Claude Sonnet 5 sessions no longer use the mid-conversation system role for harness reminders

This release includes 19 bug fixes.

• Stacked slash-skill invocations like `/skill-a /skill-b do XYZ` now load all leading skills (up to 5), not just the first
• Fixed SSL certificate errors (TLS-inspecting proxies, missing `NODE_EXTRA_CA_CERTS`, expired certs) burning retries before showing actionable guidance — they now fail immediately with the fix hint
• Fixed streaming responses being discarded when the API emits a mid-stream overloaded/server error after partial output — the partial is now kept with an incomplete-response notice
• Fixed subagents cut off by a rate limit or server error silently failing instead of returning their partial work to the parent
• Fixed subagents reporting API errors (e.g. usage limit reached) as successful results — the error is now reported to the parent agent
• Fixed the background-agent daemon on Linux killing itself and every running agent every ~50 seconds after an unclean shutdown left a corrupted worker record
• Fixed background agents failing to cold-start over SSH on macOS with "Could not switch to audit session" (regression in 2.1.196)
• Fixed `claude stop` being silently undone when it raced a background-agent respawn — the respawn now honors the stop
• Fixed background job progress indicators stalling for minutes while the job ran long commands
• Fixed background sessions on memory-starved machines showing a generic error — they now indicate low memory and suggest freeing resources
• Fixed remote sessions briefly flapping between Working and Idle in the agent view when a background agent completes
• Fixed idle subagents vanishing from the agent panel while other subagents were still working; surplus idle agents now collapse into an expandable summary row
• Fixed typing `/model` or `/fast` while viewing a subagent silently opening the lead's model picker — a notice now explains the command applies to the lead
• Fixed `SessionStart`, `Setup`, and `SubagentStart` hooks silently hiding stderr when exiting with code 2 — the error is now shown in the transcript

This release includes 2 new features and 13 bug fixes.

• Claude in Chrome is now generally available
• Added background agent notifications in `claude agents` — sessions that need input or finish now fire the `Notification` hook (`agent_needs_input` / `agent_completed`)
• Added `/dataviz` skill for chart and dashboard design guidance with a runnable color-palette validator
• Gateway: added Claude Platform on AWS (anthropicAws) as an upstream provider; model-not-found responses now advance the failover chain
• Background agents launched from `claude agents` now commit, push, and open a draft PR when they finish code work in a worktree, instead of stopping to ask
• The built-in Explore agent now inherits the main session's model (capped at opus) instead of running on haiku
• Subagents and context compaction now inherit the session's extended thinking configuration, improving output quality on delegated tasks
• Fixed brief network drops mid-response aborting the turn — transient errors like ECONNRESET now retry with backoff instead of failing
• Fixed excessive background classifier requests when sandboxed processes repeatedly accessed the same network host
• Fixed background tasks in web, desktop, and VS Code task panels getting stuck on "Running" after they finish or after resuming a session
• Fixed agent teams: a teammate that dies on an API error now reports "failed" to the lead, and messaging a stuck teammate wakes it to retry immediately
• Fixed the `/diff` panel not refreshing when you switch branches or commit outside the session
• Fixed markdown tables overflowing and wrapping their right border when rendered in fullscreen mode
• Fixed Claude Platform on AWS and Mantle sessions dead-ending with "Please run /login" when the STS token expires — `awsAuthRefresh` now runs automatically
• Fixed "no route to host" for local-network hosts in macOS background agent sessions by declaring Local Network entitlements

Introducing Claude Sonnet 5: now the default model in Claude Code, with a native 1M-token context window and promotional pricing of $2/$10 per Mtok through August 31. Update to version 2.1.197 for access. https://www.anthropic.com/news/claude-sonnet-5

• Introducing Claude Sonnet 5: now the default model in Claude Code, with a native 1M-token context window and promotional pricing of $2/$10 per Mtok through August 31. Update to version 2.1.197 for access. https://www.anthropic.com/news/claude-sonnet-5

This update introduces organization default models, improves session management and file handling, and addresses numerous bugs and security concerns across various Claude features.

• Organization admins can now set default models for their organization.
• Enhanced file attachment handling and background job reliability.
• Numerous bug fixes for agents, sessions, security, and tool integrations.

This release includes 1 new feature, 8 bug fixes, and 3 improvements.

• Added `CLAUDE_CODE_DISABLE_MOUSE_CLICKS` to disable mouse click/drag/hover in fullscreen mode while keeping wheel scroll
• Fixed hook matchers with hyphenated identifiers (e.g. `code-reviewer`, `mcp__brave-search`) accidentally substring-matching — they now exact-match. Use `mcp__brave-search__.*` to match all tools from a hyphenated MCP server.
• Fixed voice dictation on macOS capturing silence in long-running sessions after the default input device changes
• Fixed voice dictation auto-submit never firing for languages written without spaces (Japanese, Chinese, Thai)
• Fixed external plugins enabled only by project `.claude/settings.json` not requiring explicit install consent on every loader path
• Fixed `/plugin` Enable/Disable not working when a plugin's `plugin.json` `name` differs from its marketplace entry name
• Fixed background jobs disappearing from `claude agents` or losing data when written by a newer Claude Code version
• Fixed reopening a crashed background task showing a blank screen for up to 5 seconds instead of its restart
• Fixed background agent daemons running unreachable when the control socket fails to start, blocking restarts
• Improved voice mode on Linux: now distinguishes "no microphone" from "SoX not installed" when SoX is present but no audio capture device exists
• Improved `claude agents` completed list to fill available vertical space; on short terminals the header compacts so live sessions stay visible
• Improved Remote session startup with a provisioning checklist while the container starts

This release includes 6 new features, 5 bug fixes, and 4 improvements.

• Added `autoMode.classifyAllShell` setting to route all Bash/PowerShell commands through the auto-mode classifier instead of only arbitrary-code-execution patterns
• Added auto-mode denial reasons to the transcript, the denial toast, and `/permissions` recent denials
• Added `claude_code.assistant_response` OpenTelemetry log event containing the model's response text. Redacted unless `OTEL_LOG_ASSISTANT_RESPONSES=1`; when that var is unset it follows `OTEL_LOG_USER_PROMPTS`, so deployments that already log prompt content will start receiving response content on upgrade — set `OTEL_LOG_ASSISTANT_RESPONSES=0` to keep prompts-only.
• Added live file path autocomplete to bash mode (`!`)
• Added a startup notice when MCP servers need authentication, pointing at `/mcp`
• Added automatic memory-pressure reaping for idle background shell commands (disable with `CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP=1`)
• Fixed `/model` and other client-data-gated UI showing stale/empty state immediately after `/login`
• Fixed backgrounding (←←) spuriously cancelling with "N background tasks would be abandoned" when all running tasks carry over to the new session
• Fixed pinned background agents being re-prompted to "Continue from where you left off" after every auto-update
• Fixed backgrounding the main turn spawning a phantom "general-purpose (resumed)" subagent that re-ran the main conversation
• Fixed agent panel hiding sibling agents when viewing a subagent
• Improved background agents: the launch result no longer instructs Claude to "end your response" — it keeps working on other tasks while the agent runs
• Improved MCP `headersHelper` auth: the helper now re-runs and reconnects automatically when a tool call returns 401/403
• Improved plugin auto-rename: marketplace `renames` maps are now followed automatically, updating your settings to the new name

This release includes 1 new feature, 12 bug fixes, and 7 improvements.

• Added `/rewind` support for resuming a conversation from before `/clear` was run
• Fixed scroll position jumping to the bottom while reading earlier output during a streaming response
• Fixed background agents resurrecting after being stopped — stopping an agent from the tasks panel is now permanent
• Fixed `/voice` showing a generic "not available" message when disabled by an organization's policy — it now explains the restriction
• Fixed `/login` URL opening truncated in Windows Terminal when it wraps across lines
• Fixed Cmd+click on links in fullscreen mode for Ghostty over ssh/tmux
• Fixed `claude agents` sending builtin slash commands like `/usage` to background sessions as prompt text instead of showing a hint
• Fixed `claude agents` job rows showing full filesystem paths for pasted images instead of the `[Image #N]` placeholder
• Fixed hooks with comma-separated matchers (e.g. `"Bash,PowerShell"`) silently never firing
• Fixed `/permissions` Recently-denied tab: approving a denial now persists on close instead of being silently discarded
• Fixed the agent panel jumping by one row when scrolling the roster past the overflow cap
• Fixed the welcome splash art overflowing the default 80×24 macOS Terminal window
• Fixed managed settings: `forceRemoteSettingsRefresh` now takes effect when set via MDM or file policy, and the fetch sends `Cache-Control: no-cache` to prevent proxies from serving stale responses
• Improved sandbox network permission dialog: hosts you allow with "Yes" are now remembered for the rest of the session instead of re-prompting on every connection
• Improved MCP server reliability: capability discovery (`tools/list`, `prompts/list`, `resources/list`) now retries transient network errors with short backoff
• Improved MCP OAuth: discovery and token requests now retry once after transient network errors, and headless environments skip the browser popup and go straight to the paste-the-URL prompt

This release includes 3 new features, 14 bug fixes, and 3 improvements.

• Added `sandbox.credentials` setting to block sandboxed commands from reading credential files and secret environment variables
• Added org-configured model restrictions to the model picker, `--model`, `/model`, and `ANTHROPIC_MODEL`, with a "restricted by your organization's settings" message when a restricted model is selected
• Added mouse click support to select menus (permission prompts, `/model`, `/config`, etc.) in fullscreen mode
• Fixed `--resume` failing with "No conversation found" when the original `-p` run produced no model turns
• Fixed `--json-schema` and workflow `agent({schema})` structured output: the model can no longer re-call `StructuredOutput` indefinitely after a successful call, and follow-up turns now reliably return structured output
• Fixed remote MCP tool calls that hang with no response for 5 minutes — they now abort with an error instead of blocking indefinitely (override with `CLAUDE_CODE_MCP_TOOL_IDLE_TIMEOUT`)
• Fixed Claude Code Remote sessions taking ~2.7s longer to start after the agent proxy CA system-trust install was added
• Fixed pasted Korean/CJK text turning into mojibake in terminals that deliver paste as per-byte extended-key events
• Fixed `/update` over Remote Control hanging when a startup trust dialog would have shown
• Fixed background jobs in the agents view getting stuck in "working" indefinitely when the agent ended a turn without producing structured output
• Fixed channel connections dropping after navigating to the agents view and back, and after `/bg`, `/tui`, or `/update`
• Fixed agent stop notifications not correctly attributing who stopped the agent, and improved wording ("finished"/"stopped" instead of "came to rest")
• Fixed subagent depth tracking: resumed subagents now restore their original spawn depth, and forked subagents now count toward the depth cap
• Fixed leaked agent worktree registrations: locked `.git/worktrees/` entries from killed agents are now cleaned up automatically