Version 2.1.198 Release
Major release featuring subagents running in background by default, general availability of Claude in Chrome, new /dataviz skill, AWS platform support, improved agent notifications and error handling, and numerous bug fixes for agent teams, branch management, UI rendering, and network resilience.
- Subagents now run in the background by default, so Claude keeps working while they run and is notified when they finish (previously a gradual rollout)
- Claude in Chrome is now generally available
- Added background agent notifications in
claude agents— sessions that need input or finish now fire theNotificationhook (agent_needs_input/agent_completed) - Added
/datavizskill 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 agentsnow 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
/diffpanel 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 —
awsAuthRefreshnow runs automatically - Fixed "no route to host" for local-network hosts in macOS background agent sessions by declaring Local Network entitlements
- Fixed
/desktopfailing with "Cannot determine working directory" after entering and exiting a worktree - Fixed background agents repeatedly showing "Reconnecting…" every ~52 seconds on macOS while the agents view was open
- Fixed pressing
←insideclaude attach <id>exiting to the shell instead of opening the agent view - Fixed
claude --bgsilently creating an unattachable session when combined with--print/-p; the conflicting flags are now rejected up front - Fixed the workflow progress view dropping the earliest agents from the list while the phase counter stayed correct in SDK and desktop-app sessions
- Fixed
.claude/rules/conditional rules not loading when the target file is reached via a symlinked path - Fixed Cmd+click not opening URLs in fullscreen mode in Warp on macOS
- Fixed double-click word selection in fullscreen mode to select the entire URL including the scheme
- Fixed plan mode not auto-allowing read-only tool calls when a session starts in plan mode
- Fixed
/branchderiving its default fork name from the compaction summary instead of the first real prompt - Improved focus mode: subagents launched in a turn now appear in its activity summary, and completed background notifications fold into a single count
- Improved syntax highlighting accuracy in code blocks, diffs, and file previews by upgrading to highlight.js 11
- Keyboard shortcut hints now show opt/cmd instead of alt/super when connected from a Mac over SSH
- Improved API retry UX: the error reason is now shown after the second attempt, and a status page link replaces the spinner tip when the API is overloaded
/loginnow opens the sign-in dialog from theclaude agentsview instead of saying it isn't available- Subagents now treat messages from the agent that launched them as normal task direction; an agent's message is still never treated as the user's approval
- Removed the
/agentswizard; ask Claude to create or manage subagents, or edit.claude/agents/directly
Source: original entry ↗
More from Claude Code
Follow Claude Code to get its new changes in your feed and email digest.
Fixed prompt and agent hooks handling for instruction-based blocking
Fixed a bug where prompt and agent hooks written as blocking instructions were not working correctly. Improved evaluation of Stop and SubagentStop hooks so Claude is less likely to stop early when hooks are written as conditional instructions.
Claude Code 2.1.293
Released version 2.1.293 with Claude Haiku 5.5 as the default Haiku model featuring 1M context window, expanded agent functionality with agentType and isDeferred fields, and numerous bug fixes across context management, MCP connections, vim mode, permissions, and cloud sessions.
Claude Code 2.1.292 Release
Claude Code 2.1.292 includes new features like marketplace source support for plugin installation, effort parameters for agent tools, and prompt caching for mods. This release also addresses numerous security fixes including permission bypass issues, file access restrictions, and cache tampering vulnerabilities, plus improvements to session handling, auto mode restoration, and various UI/UX fixes.