Claude Code
TL;DR
- OTel now logs assistant responses by default when you already log prompts. The new
claude_code.assistant_responseevent followsOTEL_LOG_USER_PROMPTSunless you setOTEL_LOG_ASSISTANT_RESPONSES=0. - Idle background shell commands now get reaped under memory pressure. Disable with
CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP=1if you depend on long-lived background processes. autoMode.classifyAllShellroutes every Bash/PowerShell command through the auto-mode classifier. Opt-in setting; previously only arbitrary-code-execution patterns triggered classification. (more below)- MCP
headersHelperauto-reconnects on 401/403. If your MCP auth tokens expire mid-session, the helper now re-runs and reconnects without manual intervention.
New in 2.1.193, 2.1.191, 2.1.190
2.1.193 (June 26, 2026)
- Added
autoMode.classifyAllShellsetting 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
/permissionsrecent denials - Added
claude_code.assistant_responseOpenTelemetry log event containing the model's response text. Redacted unlessOTEL_LOG_ASSISTANT_RESPONSES=1; when that var is unset it followsOTEL_LOG_USER_PROMPTS, so deployments that already log prompt content will start receiving response content on upgrade. SetOTEL_LOG_ASSISTANT_RESPONSES=0to 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
/modeland 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
headersHelperauth: the helper now re-runs and reconnects automatically when a tool call returns 401/403 - Improved plugin auto-rename: marketplace
renamesmaps are now followed automatically, updating your settings to the new name - Improved
/add-dirmessage when the directory is already a working directory
2.1.191 (June 26, 2026)
- Added
/rewindsupport for resuming a conversation from before/clearwas 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
/voiceshowing a generic "not available" message when disabled by an organization's policy, it now explains the restriction - Fixed
/loginURL 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 agentssending builtin slash commands like/usageto background sessions as prompt text instead of showing a hint - Fixed
claude agentsjob 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
/permissionsRecently-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 80x24 macOS Terminal window
- Fixed managed settings:
forceRemoteSettingsRefreshnow takes effect when set via MDM or file policy, and the fetch sendsCache-Control: no-cacheto 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
- Improved MCP error messages: HTTP 404 errors now show the URL and point to your MCP config
- Improved vim mode prompt-history search (NORMAL
/) to hint how to reach slash commands - Reduced CPU usage during streaming responses by ~37% by coalescing text updates to 100ms
- Reduced long-session memory growth from terminal output cache
2.1.190 (June 26, 2026)
- Bug fixes and reliability improvements
Notes
Auto-mode classifier scope
2.1.183 started the tighter-auto-mode arc by blocking destructive git commands unless you explicitly asked for them. 2.1.178 extended it to subagent spawns (the classifier now evaluates a subagent before it launches). classifyAllShell is the logical next step: every shell command, not just known-dangerous patterns, passes through the classifier before execution. If you use auto mode in production pipelines, this setting is worth enabling and testing against your common commands to see how many get flagged.