Claude Code v2.1.192 to v2.1.193 Major Updates
This page has been translated by machine translation. View original
This is Ishikawa from the Cloud Business Division. Claude Code v2.1.193 (released June 25, 2026) has been released. This update focuses on enhanced safety and visibility for auto-mode (automatic execution mode) and bug fixes around background agents. Note that v2.1.192, which preceded this article, is a missing version not published in either npm or the CHANGELOG, so we will cover the existing v2.1.193 here.
Update Summary
v2.1.193 includes 15 changes. New features include the autoMode.classifyAllShell setting and automatic memory reclamation for background shells, while fixes resolve multiple bugs around backgrounding. Additionally, new log events have been added to OpenTelemetry, and care is needed as behavior will change when upgrading with existing settings.
Highlighted Updates
- New Features: Live file path completion has been added to bash mode (
!). Additionally, a notification is now shown at startup when an MCP server requires authentication. - Bug Fixes: Multiple bugs related to backgrounding have been resolved together. Issues such as "phantom sub-agents" being generated that re-execute the conversation when the main turn is backgrounded have been resolved.
- Security: The
autoMode.classifyAllShellsetting has been added to route all Bash/PowerShell commands through the auto-mode classifier. Additionally, a log event containing model response text has been added to OpenTelemetry (see "Breaking Changes & Deprecations" below).
Update Details
New Features
- Addition of
autoMode.classifyAllShellsetting: All Bash/PowerShell commands will now be routed through the auto-mode classifier. Previously, only "arbitrary-code-execution patterns" were classified, but enabling this setting applies a gate to all commands. - Visibility of auto-mode rejection reasons: Auto-mode rejection reasons are now displayed in the transcript, rejection toast, and the recent rejections list in
/permissions. This allows you to trace why something was rejected. - Live file path completion in bash mode: In bash mode (
!), file paths can now be live-completed while typing commands. - Startup notification for MCP authentication: When an MCP server requires authentication, the startup notification now guides users to
/mcp. - Automatic memory reclamation for background shells: Idle background shell commands are now automatically reaped when memory is under pressure. This can be disabled with
CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP=1.
Improvements
- Background agent launch results: Launch results no longer instruct Claude to "end your response," allowing other tasks to continue while the agent is running.
- Automatic re-authentication for MCP
headersHelper: When a tool call returns 401/403,headersHelpernow automatically re-runs and reconnects. - Automatic plugin renaming: The marketplace
renamesmap is now automatically followed, updating settings to new names. /add-dirmessage: The message has been improved for when the specified directory is already the working directory.
Fixes
- Fixed phantom sub-agent generation when backgrounding the main turn: Resolved an issue where backgrounding the main turn would generate a sub-agent called "general-purpose (resumed)" that re-executed the main conversation.
- Fixed backgrounding being incorrectly cancelled: Resolved an issue where backgrounding (←←) would incorrectly display "N background tasks would be abandoned" and cancel, even though all running tasks would be handed off to the new session.
- Fixed re-prompting of pinned background agents: Resolved an issue where pinned background agents would be prompted with "Continue from where you left off" again with each automatic update.
- Additionally, display issues with UI that depends on client data (such as
/modelimmediately after/login) and an issue where the agent panel hides sibling agents when displaying sub-agents have also been fixed.
Breaking Changes & Deprecations
A claude_code.assistant_response log event containing model response text has been added to OpenTelemetry. By default it is redacted, but if OTEL_LOG_ASSISTANT_RESPONSES is not set, it follows the OTEL_LOG_USER_PROMPTS setting.
Therefore, deployments that are already logging prompt content with OTEL_LOG_USER_PROMPTS=1 will start logging response content as well after upgrading. If you want to keep logging only prompts as before, explicitly set OTEL_LOG_ASSISTANT_RESPONSES=0.
Since logs may contain sensitive information, we recommend verifying the behavior before upgrading in environments where OpenTelemetry is enabled.
In Closing
v2.1.193 is an update focused on enhanced safety and visibility for auto-mode and bug fixes around background agents. For those who frequently use backgrounding, multiple experience improvements can be expected. On the other hand, please be aware that in environments running OpenTelemetry, the logging behavior for response text will change upon upgrading. Why not give the update a try?
References