Claude Code 2.1.198 has been released. 32 CLI changes Highlights: • Claude in Chrome is generally available, offering direct browser access to sessions and agents with no install • Background agents auto-commit, push, and open draft PRs in worktree after finishing code, automating delivery • Docs now advise grep for searches and clarify head_limit/unlimited/offset semantics to reduce surprises Complete details in thread ↓

Claude Code CLI 2.1.198 changelog: New features: • 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 Fixes: • 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 • Fixed /desktop failing 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 ← inside claude attach exiting to the shell instead of opening the agent view • Fixed claude --bg silently 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 /branch deriving its default fork name from the compaction summary instead of the first real prompt Improvements: • 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 • 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 Removal: • Removed the /agents wizard; ask Claude to create or manage subagents, or edit .claude/agents/ directly Other changes: • Claude in Chrome is now generally available • 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 • Keyboard shortcut hints now show opt/cmd instead of alt/super when connected from a Mac over SSH • /login now opens the sign-in dialog from the claude agents view 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 Source: #21198" target="_blank" rel="nofollow noopener">github.com/anthropics/cla…

@ClaudeCodeLog Chrome access is nice, but auto-commit + draft PR is the sharp part. If background agents can finish while I’m away, I want the review to show: files changed, tests run, and where it needed input. Otherwise the PR is just a polished surprise.

@ClaudeCodeLog Auto-committing background agents turn speed into a liability without tight feedback loops. The non-obvious truth is that every automated commit tests your prompt more than your code - how are you catching misinterpretations before they

Up late and bored? Tap into live conversations.

@ClaudeCodeLog background agent opens a draft PR while you sleep bro the robot is doing more standup updates than half my coworkers

@ClaudeCodeLog background agents opening PRs is a real workflow shift. the next layer is the boring stuff: repo permissions, branch policy, review packets, and a clear human approval gate before anything deploys.

@ClaudeCodeLog How can i control claude code from my mobile. Like give instructions on the same conversation / check the output or reply , the task at hand?

@ClaudeCodeLog 后台代理自动开草稿 PR 这步挺省心

@ClaudeCodeLog How stable are the background agent auto-commits?

@ClaudeCodeLog Helloitsoctocat

@ClaudeCodeLog version 2.1.198 and we casually slipping in browser access like thats not a huge deal 💀

@ClaudeCodeLog Chromeから直接エージェントに触れる進化、実運用目線で本当にありがたいです

@ClaudeCodeLog background agents auto-committing prs is wild, how's the merge conflict handling.

@ClaudeCodeLog background agents auto-committing and opening draft PRs is the one that actually changes the workflow, everything else is polish on top

@ClaudeCodeLog Auto PR creation changes the “last mile” of coding more than people realize.

@ClaudeCodeLog Did you remove the spyware?