---
title: "Claude Code 2.1.198 Makes Claude in Chrome Generally Available, Lets Background Agents Commit, Push, and Open Draft PRs, Adds `/dataviz` Skill, and Brings Claude Platform on AWS to the Gateway"
description: "Anthropic released Claude Code [v2.1.198](https://github.com/anthropics/claude-code/releases/tag/v2.1.198) on 2026-07-01T20:45:36Z, the second consecutive day of Claude Code shipping after v2.1.197 (the Sonnet 5 default release) the day before. The headline change is that Claude in Chrome is now generally available inside Claude Code: the browser-side assistant that was a research preview moves to a stable channel and is no longer gated behind a feature flag or a waitlist. The release also lands the first end-to-end automation for background agents in `claude agents`, which now commit, push, and open a draft pull request when they finish code work in a worktree, instead of stopping to ask for permission. Other notable additions: a `/dataviz` skill for chart and dashboard design with a runnable color-palette validator, a Gateway upstream for Claude Platform on AWS (`anthropicAws`) with model-not-found responses advancing the failover chain, a built-in Explore agent that now inherits the main session's model (capped at opus) instead of running on Haiku, and subagents that inherit the parent session's extended thinking configuration. The release also removes the `/agents` wizard and replaces it with the conversational flow, fixes a long list of reliability bugs around background agents, network drops, and platform auth, and improves syntax highlighting by upgrading to highlight.js 11."
date: 2026-07-02
image: "/images/heroes/2026-07-02--claude-code-2-1-198-chrome-ga-background-agents-auto-pr.png"
author: lschvn
tags: ["ai", "tooling"]
tldr:
  - "[Claude Code v2.1.198](https://github.com/anthropics/claude-code/releases/tag/v2.1.198) (released 2026-07-01T20:45:36Z) makes Claude in Chrome generally available. Claude in Chrome is the browser-side assistant that reads the page you are on, runs multi-step actions, and integrates with Claude Code and Claude Desktop; the research preview gates come off in the same release that ships Sonnet 5 as the default model (from v2.1.197 the day before). The GA build keeps the same permission model the beta had: tab-group isolation by default, the in-product permissions gate honored for concurrent CLI sessions, and the same beta-feature warnings about browser-context risks."
  - "Background agents launched from `claude agents` now commit, push, and open a draft pull request when they finish code work in a worktree, instead of stopping to ask. The release adds two new `Notification` hook events (`agent_needs_input` and `agent_completed`) so external tools can react to background agents finishing or blocking on input, and it removes the `/agents` wizard in favor of asking Claude directly or editing `.claude/agents/` by hand. The built-in Explore agent now inherits the main session's model (capped at Opus) instead of running on Haiku, and subagents and context compaction now inherit the parent session's extended thinking configuration, which improves output quality on delegated tasks."
  - "Gateway gets a new upstream provider (Claude Platform on AWS, exposed as `anthropicAws`) with model-not-found responses advancing the failover chain. The release adds a `/dataviz` skill for chart and dashboard design with a runnable color-palette validator, fixes a long list of background-agent reliability bugs (stuck `Running` status, reconnecting every 52s on macOS, dead-end `'Please run /login'` on STS token expiry, network drops aborting the turn), and upgrades syntax highlighting in code blocks, diffs, and file previews to highlight.js 11. The release follows the [v2.1.197 Sonnet 5 default piece](/articles/2026-07-01--claude-sonnet-5-default-model-claude-code-1m-context) from the day before."
faq:
  - question: "What changed in Claude Code 2.1.198?"
    answer: "Claude Code 2.1.198 (released 2026-07-01T20:45:36Z) is a feature release that ships on the day after v2.1.197 made Sonnet 5 the default model. The headline change is that Claude in Chrome is now generally available inside Claude Code. The release also adds end-to-end automation for background agents (they now commit, push, and open a draft pull request when they finish code work in a worktree), a new `Notification` hook surface (`agent_needs_input`, `agent_completed`), a `/dataviz` skill for chart and dashboard design with a runnable color-palette validator, a Gateway upstream for Claude Platform on AWS, a built-in Explore agent that inherits the main session's model (capped at Opus), subagents that inherit the parent session's extended thinking configuration, and a long list of bug fixes around background-agent reliability, network drops, and platform auth. The release also removes the `/agents` wizard and upgrades syntax highlighting to highlight.js 11."
  - question: "What does Claude in Chrome GA mean in Claude Code?"
    answer: "Claude in Chrome is the browser-side assistant that runs inside Chrome and can read the page you are on, click through forms, and chain multi-step actions, integrated with Claude Code and Claude Desktop. The GA build in v2.1.198 takes the feature out of the research-preview gate: it no longer needs a feature flag or a waitlist, the install path is the standard Claude for Chrome extension, and the in-product permissions gate is honored across concurrent CLI sessions. The permission model stays the same as the beta: tab-group isolation by default, an explicit in-product permission prompt for sensitive actions, and the same beta-feature warnings about browser-context risks. For Claude Code users, the practical change is that the same agent that drives the terminal can now drive a Chrome tab without leaving the session."
  - question: "How does the new background agent auto-PR flow work?"
    answer: "When a background agent launched from `claude agents` finishes code work in a worktree, it now commits the changes to the worktree branch, pushes the branch, and opens a draft pull request on the upstream repository, instead of stopping to ask whether to do so. The new `Notification` hook surface exposes two new events: `agent_needs_input` (fired when the agent blocks on a question) and `agent_completed` (fired when the agent finishes, successfully or otherwise). External tools can subscribe to these events to drive dashboards, send chat pings, or chain the result into a follow-up agent. The auto-PR flow is on by default for agents launched in worktrees; the legacy `stop to ask` flow is still available for agents that prefer to keep changes local."
  - question: "What is the `/dataviz` skill?"
    answer: "`/dataviz` is a new built-in skill that gives Claude Code design guidance for charts and dashboards, paired with a runnable color-palette validator. The skill loads on demand when a Claude Code session is asked to produce a chart, a dashboard, or a data visualization, and applies the same accessibility, contrast, and color-encoding rules that Anthropic uses internally. The color-palette validator is runnable: it accepts a proposed palette and reports whether it clears the contrast and color-blindness thresholds the skill encodes, so the agent can iterate on a palette without leaving the session. The skill is additive and lives next to the other built-in skills like `/init` and `/review`."
  - question: "What is the new Gateway upstream for Claude Platform on AWS?"
    answer: "The Claude Code Gateway now accepts Claude Platform on AWS (the AWS-hosted Claude API) as an upstream provider, exposed under the `anthropicAws` identifier. Model-not-found responses from one upstream now advance the failover chain to the next, so a session that points at multiple providers (for example, Claude Platform on AWS in production, Bedrock in staging) will fall through to a working provider when the requested model is unavailable on the first one. The release also fixes a dead-end where Claude Platform on AWS and Mantle sessions landed on `'Please run /login'` when the STS token expired; `awsAuthRefresh` now runs automatically. Remote Control stays disabled when `ANTHROPIC_BASE_URL` points at a non-Anthropic host, matching the existing behavior under `CLAUDE_CODE_USE_BEDROCK` / `_VERTEX` / `_FOUNDRY`."
  - question: "Why did the Explore agent change from Haiku to the main session's model?"
    answer: "The built-in Explore agent, which is the subagent that Claude Code launches for read-only file exploration, used to run on Haiku regardless of the parent session's model. In v2.1.198 it inherits the main session's model, capped at Opus. The change is a quality-of-output improvement: a Sonnet 5 main session that delegates a codebase-wide exploration to the Explore subagent now gets a Sonnet 5 answer instead of a Haiku answer, and the agent's planning and tool use match the rest of the session. The Opus cap is a cost guardrail so a session that picked Opus as the main model does not silently cascade into an Opus-powered Explore pass on every sub-call. Subagents and context compaction now also inherit the parent session's extended thinking configuration, so the delegation does not lose the effort level the main session picked."
  - question: "What happened to the `/agents` wizard?"
    answer: "The `/agents` slash command used to open a multi-step wizard for creating and managing subagents. v2.1.198 removes the wizard and routes the same intent through the conversational flow (ask Claude to create or manage a subagent) and through direct file editing of `.claude/agents/`. The change is meant to make subagent configuration live closer to the other agent files in the repo and to remove a UI path that diverged from the natural way to talk to Claude about subagents. The `claude agents` view for background agents is unchanged; only the `/agents` slash command is removed."
  - question: "Is Claude Code 2.1.198 safe to upgrade to today?"
    answer: "Yes. The release is the second of two consecutive Claude Code releases (after v2.1.197 the day before), it ships on a stable channel, and the new features are additive: the background-agent auto-PR flow, the `/dataviz` skill, the Gateway `anthropicAws` upstream, the new Notification hook events, and the Explore-agent model upgrade all default on without breaking existing sessions. The only behavior change worth flagging is the removal of the `/agents` wizard, which is a one-line `claude agents` rewrite for any team that scripted around it. The recommended transition is to update Claude Code (`claude update` or the in-app update prompt), confirm the GA Chrome extension is installed, and re-run any background-agent workflow that used to stop to ask to confirm the auto-PR flow is what you want."
---

[Claude Code v2.1.198](https://github.com/anthropics/claude-code/releases/tag/v2.1.198) shipped on 2026-07-01T20:45:36Z, one day after [v2.1.197](https://github.com/anthropics/claude-code/releases/tag/v2.1.197) made Sonnet 5 the default model. The release makes Claude in Chrome generally available, lets background agents commit/push/open a draft pull request when they finish code work in a worktree, adds a `/dataviz` skill for chart and dashboard design, and brings Claude Platform on AWS to the Gateway. The release follows a week of Claude Code activity that started with the [v2.1.195 background-agent reliability pass](https://github.com/anthropics/claude-code/releases/tag/v2.1.195) and continued through the [v2.1.196 org-default model and MCP trust fix](https://github.com/anthropics/claude-code/releases/tag/v2.1.196) and the v2.1.197 Sonnet 5 default. v2.1.198 is the broadest of the four: it is a feature release that lands end-to-end automation, a GA browser-side assistant, a new Gateway upstream, and a quality-of-output upgrade for the Explore subagent, alongside the usual bug-fix tail.

The Sonnet 5 launch was the bigger individual event this week, and the [Claude Code Sonnet 5 default piece](/articles/2026-07-01--claude-sonnet-5-default-model-claude-code-1m-context) covered the v2.1.197 model swap and the cyber safeguards in detail. v2.1.198 is the release that builds the product around Sonnet 5: the GA Chrome experience, the background-agent workflow that runs while the developer is away, the `/dataviz` skill for the dashboards that the agent now ships, and the Gateway upstream that lets the same session run on Claude Platform on AWS.

## Claude in Chrome is now GA inside Claude Code

The headline change is the [general availability of Claude in Chrome](https://github.com/anthropics/claude-code/releases/tag/v2.1.198). The product has been in research preview since August 2025 and was gated behind a feature flag, a waitlist, and the beta-feature warnings on the [Claude for Chrome page](https://claude.com/claude-for-chrome). v2.1.198 takes the gates off inside Claude Code: the same install path that worked for the beta is now the stable path, the in-product permissions gate is honored across concurrent CLI sessions (closing a regression where the gate was off for second-session CLI), and the tab-group isolation default is preserved. The release keeps the same beta-feature warnings on the [Claude for Chrome marketing page](https://claude.com/claude-for-chrome) because the page documents the standalone Chrome extension; the in-Claude Code integration is what moves to GA.

For Claude Code users, the practical change is that the agent that drives the terminal can now drive a Chrome tab without leaving the session. A user can ask Claude Code to fill a form, click through a multi-page flow, or extract structured data from a page, and the agent handles the browser side the same way it handles the terminal side. The permission model is the same as the beta: tab-group isolation by default, an explicit in-product permission prompt for sensitive actions, and the same browser-context risk warnings. The release does not introduce a new permission tier; it just removes the gates that made the feature inaccessible by default.

## Background agents now ship the diff

The biggest product change in v2.1.198 is end-to-end automation for background agents launched from `claude agents`. Before this release, a background agent that finished code work in a worktree stopped to ask whether to commit, push, or open a pull request. The v2.1.198 release flips the default: the agent commits the changes to its worktree branch, pushes the branch, and opens a draft pull request on the upstream repository. The new `Notification` hook surface exposes two events for external tools to subscribe to: `agent_needs_input` (fired when the agent blocks on a question) and `agent_completed` (fired when the agent finishes, successfully or otherwise). The hook events are the integration point for dashboards, chat pings, and follow-up agents; the auto-PR flow is the integration point for the developer's working repo.

The same release also hardens the background-agent reliability surface. v2.1.198 fixes a regression where background tasks in web, desktop, and VS Code task panels got stuck on `Running` after they finished or after the session was resumed; a bug where background agents repeatedly showed `Reconnecting…` every 52 seconds on macOS while the agents view was open; and a deadlock where `claude --bg` silently created an unattachable session when combined with `--print` / `-p` (the conflicting flags are now rejected up front). Agent teams get a fix where a teammate that dies on an API error now reports `failed` to the lead, and messaging a stuck teammate wakes it to retry immediately. The release also cleans up a leaked worktree registration: locked `.git/worktrees/` entries from killed agents are now removed automatically.

## `/dataviz` skill, Gateway on AWS, Explore agent upgrade

Three smaller but practical additions round out the release. The new [`/dataviz` skill](https://github.com/anthropics/claude-code/releases/tag/v2.1.198) gives Claude Code design guidance for charts and dashboards and ships with a runnable color-palette validator. The skill loads on demand when a session is asked to produce a chart or a dashboard and applies the same accessibility, contrast, and color-encoding rules that Anthropic uses internally; the validator accepts a proposed palette and reports whether it clears the contrast and color-blindness thresholds the skill encodes. The skill is additive and lives next to the other built-in skills like `/init` and `/review`.

The Claude Code Gateway now accepts Claude Platform on AWS as an upstream provider, exposed under the `anthropicAws` identifier. Model-not-found responses from one upstream advance the failover chain to the next, so a session that points at multiple providers (for example, Claude Platform on AWS in production and Bedrock in staging) falls through to a working provider when the requested model is unavailable on the first one. The release also fixes a dead-end where Claude Platform on AWS and Mantle sessions landed on `'Please run /login'` when the STS token expired: `awsAuthRefresh` now runs automatically. Remote Control stays disabled when `ANTHROPIC_BASE_URL` points at a non-Anthropic host, matching the existing behavior under `CLAUDE_CODE_USE_BEDROCK` / `_VERTEX` / `_FOUNDRY`.

The built-in Explore agent, which is the subagent that Claude Code launches for read-only file exploration, now inherits the main session's model (capped at Opus) instead of running on Haiku. The change is a quality-of-output improvement: a Sonnet 5 main session that delegates a codebase-wide exploration to the Explore subagent now gets a Sonnet 5 answer instead of a Haiku answer. The Opus cap is a cost guardrail so a session that picked Opus as the main model does not silently cascade into an Opus-powered Explore pass on every sub-call. Subagents and context compaction also now inherit the parent session's extended thinking configuration, so the delegation does not lose the effort level the main session picked.

## Smaller fixes worth flagging

The v2.1.198 release notes close a long tail of small fixes. Brief network drops mid-response (`ECONNRESET`) now retry with backoff instead of aborting the turn. Excessive background classifier requests when sandboxed processes repeatedly accessed the same network host are fixed. The `/diff` panel now refreshes when the user switches branches or commits outside the session. Markdown tables no longer overflow and wrap their right border when rendered in fullscreen mode. The `/desktop` command no longer fails with `Cannot determine working directory` after entering and exiting a worktree. The workflow progress view no longer drops the earliest agents from the list while the phase counter stays correct in SDK and desktop-app sessions. `.claude/rules/` conditional rules now load when the target file is reached via a symlinked path. Plan mode now auto-allows read-only tool calls when a session starts in plan mode. The `/branch` default fork name is now derived from the first real prompt instead of the compaction summary. Syntax highlighting accuracy in code blocks, diffs, and file previews improves by upgrading to highlight.js 11. Keyboard shortcut hints now show opt/cmd instead of alt/super when connected from a Mac over SSH. The API retry UX shows the error reason after the second attempt and replaces the spinner tip with a status-page link when the API is overloaded. `/login` now opens the sign-in dialog from the `claude agents` view instead of saying it is not 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.

## Why this matters for Claude Code users

The v2.1.198 release is the second of two consecutive Claude Code releases that ship Sonnet 5 as the new default. v2.1.197 was the model swap; v2.1.198 is the product that runs on top of the swap. The GA Chrome experience, the background-agent auto-PR workflow, the `/dataviz` skill, and the Gateway `anthropicAws` upstream are the four changes that a working Claude Code user notices on a Tuesday morning after `claude update`. The reliability tail (network-drop retry, STS auto-refresh, worktree registration cleanup, hook events for external tools) is what a team running Claude Code in CI or against a fleet of repos notices over the next month. Both land in the same release, and the release is the broadest feature Claude Code has shipped since the v2.1.196 org-default model and MCP trust fix the day before v2.1.197.

The release also pulls Claude Code closer to a "set it and forget it" workflow for tasks that take longer than a single session. A team that delegates a refactor to a background agent now gets a draft PR in their inbox instead of a stop-to-ask prompt. A team that wants to track background agents across multiple repositories can wire the new `Notification` hook events into a dashboard. A team that runs Claude Code against a Chrome tab now has the GA version of the feature instead of a research preview. The release is the first one in 2026 where the headline changes are about delegation and integration rather than about the model itself, and it sets the template for the next release cycle: the model is settled, and the work is on the product around it.