← Back
FeaturedAIModels#Anthropic#AWS#Chrome Integration#Claude Code#Background Agent

Claude Code v2.1.198 Released: Chrome Integration and Background Agent Notifications

Claude Code:GitHub Releases(RSS)T1.5
04:4507/02, 04:45 AMGitHub ReleaseRead the original ↗Export MD ↓

Score

71

Why selected

Includes multiple user-requested fixes and features such as Chrome extension, background notifications, chart skill, but is a minor version iteration, scoring 75.

AI commentary

「This update significantly enhances Claude Code's integration capabilities, background task reliability, and developer experience, especially with Chrome extension and agent notifications enabling smoother cross-platform collaboration.」

Quick overview

Claude Code v2.1.198 highlights: Claude in Chrome is now generally available; background agent notifications added (hooks agent_needs_input / agent_completed); new /dataviz skill for chart/dashboard design with a runnable color-palette validator; Gateway adds Anthropic AWS as an upstream provider. Multiple fixes include network retry on transient errors, background tasks stuck on 'Running', markdown table overflow, macOS background agent local network routing, .claude/rules symlink loading, and more. Improvements to focus mode, syntax highlighting, and keyboard shortcuts.

  • Claude in Chrome extension is now generally available
  • New background agent notification hooks for input needs and completion
  • New /dataviz skill for chart and dashboard design with runnable palette validator
  • Gateway adds Anthropic AWS upstream provider; multiple stability fixes

Full text

Showing the source text; the full translation is being generated.

Uh oh!

There was an error while loading. Please reload this page.

anthropics / claude-code Public Additional navigation options
  1. Releases
  2. v2.1.198

v2.1.198

Compare

Choose a tag to compare

Sorry, something went wrong.

Filter Loading

Sorry, something went wrong.

Uh oh!

There was an error while loading. Please reload this page.

No results found

View all tags @ashwin-ant ashwin-ant released this 01 Jul 20:45 v2.1.198 75709ea

What's changed

  • 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 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
  • 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
  • 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 <id> 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
  • 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
  • /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
  • Removed the /agents wizard; ask Claude to create or manage subagents, or edit .claude/agents/ directly
Assets 12 Loading

Uh oh!

There was an error while loading. Please reload this page.

👍 19 mike1858, avoylenko, raky291, saita08, AlexandrosKyriakakis, eyoboue, santimentasti, egoan82, Luminous-Works, ccn-you-sunghwa, and 9 more reacted with thumbs up emoji 😄 3 mike1858, saita08, and distinguished-sre reacted with laugh emoji 🎉 5 mike1858, saita08, vimalspaceton618-afk, thinh9e, and simono reacted with hooray emoji ❤️ 8 mike1858, saita08, wearemssatoshi, leesdonson, jsaristi, Juan131ng, robinpie, and Mateo728 reacted with heart emoji 🚀 5 mike1858, saita08, mrverdant13, egoan82, and MISSMISCHA666 reacted with rocket emoji 👀 3 mike1858, saita08, and distinguished-sre reacted with eyes emoji All reactions
  • 👍 19 reactions
  • 😄 3 reactions
  • 🎉 5 reactions
  • ❤️ 8 reactions
  • 🚀 5 reactions
  • 👀 3 reactions
28 people reacted

Related items

92
08:00OpenRouter:Announcements(RSS)T1RSS

FeaturedDeepSeek V4 Doubles Token Share on OpenRouter, Driven by Agentic Workloads

DeepSeek V4 在 OpenRouter 上的代币份额翻倍,智能体工作负载成主要驱动力

The rapid adoption of DeepSeek V4 signals a strong market preference for high-performance, low-cost inference models, especially as agentic use cases reshape AI deployment.

AIModels#DeepSeek#OpenRouter#V4 Flash
91

Five-dimension score

Information gain9 ×0.3

详细揭示了两个具体设置如何协同作用实现三倍性能提升,信息增量高。

Content quality8 ×0.2

来自OpenAI官方,数据明确,结构清晰,但缺少对比实验细节。

Practical value9 ×0.2

为AI工程师提供了可直接操作的性能调优方案,实用性强。

Timeliness10 ×0.15

消息刚发布,具有高度时效性。

Source reliability10 ×0.15

信源为OpenAI官方新闻,权威可靠。

Base 91 × T1 Source weight ×1 = 91

Curation line 60Selected

23:00OpenAI:News(RSS)T1RSS

FeaturedEnabling Two Settings Triples ARC-AGI-3 Benchmark Scores

启用两项设置使ARC-AGI-3基准测试分数提升三倍

This finding is crucial! It shows that model performance depends not only on training but also on inference-time configuration. For AI engineers and researchers, this is a must-know optimization direction. Teams deploying models on resource-constrained devices in particular could find a low-cost way to boost capabilities.

TechModels#ARC-AGI-3#GPT-5.6#OpenAI
91

Five-dimension score

Information gain9 ×0.3

首次公开GPT-5.6具体效率优化细节,此前仅有传闻。

Content quality8 ×0.2

内容简洁,关键指标明确,但缺乏详细技术文档支撑。

Practical value9 ×0.2

直接指导企业如何降低AI部署成本,具有商业参考价值。

Timeliness10 ×0.15

刚发布的官方新闻,时效性极强。

Source reliability10 ×0.15

来源为OpenAI官方博客,信源权威。

Base 91 × T1 Source weight ×1 = 91

Curation line 60Selected

08:00OpenAI:News(RSS)T1RSS

FeaturedGPT-5.6: Fusing Frontier Intelligence with Frontier Efficiency

GPT-5.6:前沿智能与前沿效率的融合

This news is worth watching as it marks a shift from pure parameter scaling to efficiency competition. For AI developers and business decision-makers, GPT-5.6 means higher performance at lower cost, especially for long-context or agentic tasks previously hindered by inference expenses. OpenAI's move may redefine what 'frontier' means.

AIModels#Agent Workflows#GPT-5.6#OpenAI
91

Five-dimension score

Information gain8 ×0.3

首次提出针对CPU优化的1M上下文模型,填补了边缘设备长文本推理的空白,信息增量显著。

Content quality9 ×0.2

技术细节清晰,提供了基准测试对比和架构解释,图文并茂,质量上乘。

Practical value10 ×0.2

直接降低长上下文应用的硬件成本,开源权重可立即部署,实用价值极高。

Timeliness10 ×0.15

当日发布的博客,且长上下文推理是当前AI热点,时效性满分。

Source reliability9 ×0.15

Hugging Face官方博客,作者为Liquid AI,属于第一方技术发布,可信度高。

Base 90.5 × T1 Source weight ×1 = 91

Curation line 60Selected

23:01Hugging Face:Blog(RSS)T1RSS

FeaturedLFM2.5-Encoders: New Models for Fast Long-Context Inference on CPU

LFM2.5-Encoder:面向CPU快速长上下文推理的新模型

This blog post catches my eye because it directly solves the pain point of running long-context LLMs on CPU. For teams or individual developers without high-end GPUs, the LFM2.5-Encoder series offers a ready-to-use open-source solution. Highly recommended for those working on RAG, document search, or code analysis—now a standard server can handle million-token documents.

AIModels#CPU Inference Optimization#LFM2.5-Encoder#Liquid AI
91

Five-dimension score

Information gain9 ×0.3

首次公开自动化红队系统的具体机制与实验发现,信息增量高。

Content quality8 ×0.2

来自官方,结构清晰,但未提供完整技术细节(如具体模型版本),扣1分。

Practical value9 ×0.2

对AI安全工程师、模型开发者和企业部署者直接指导作用,实用性极强。

Timeliness10 ×0.15

刚刚发布,是当前AI安全领域最前沿进展之一。

Source reliability10 ×0.15

信源为OpenAI官方新闻,权威且一手。

Base 91 × T1 Source weight ×1 = 91

Curation line 60Selected

18:00OpenAI:News(RSS)T1RSS

FeaturedGPT-Red: OpenAI Automates Red Teaming via Self-Play to Boost Model Robustness

GPT-Red:OpenAI通过自我对弈实现AI红队自动化,提升模型鲁棒性

GPT-Red marks a milestone from human to automated red-teaming—essential for safety engineers and alignment researchers. While reducing cost, it also raises ethical questions about automated attacks, worth pondering for everyone in AI governance.

AIModels#AI Safety Alignment#GPT-Red#OpenAI
91

Five-dimension score

Information gain9 ×0.3

这是首个针对AI模型生物安全的漏洞赏金计划,为行业提供了全新的安全评估视角。

Content quality9 ×0.2

官方来源,内容清晰,涵盖范围、奖励、准则等关键细节。

Practical value8 ×0.2

对AI安全研究员和生物安全专家有直接参与价值,但普通用户关联度较低。

Timeliness10 ×0.15

刚刚发布,完全符合新闻时效要求。

Source reliability10 ×0.15

OpenAI官方RSS和博客,信源权威可靠。

Base 91 × T1 Source weight ×1 = 91

Curation line 60Selected

18:00OpenAI:News(RSS)T1RSS

FeaturedOpenAI Launches GPT-5.5 Bio Bug Bounty Program

OpenAI推出GPT-5.5生物漏洞赏金计划

This program deserves attention as it pioneers the extension of AI bug bounty to biosecurity, offering a new research direction for the security community and a practical training ground for AI risk governance. It is particularly important for model safety researchers, biosecurity experts, and practitioners concerned about dual-use AI risks.

AIModels#Bio Bug Bounty#GPT-5.5#OpenAI
91

Five-dimension score

Information gain8 ×0.3

公布了vLLM新后端的具体架构设计与实测数据,对了解推理优化前沿有较高信息增量。

Content quality9 ×0.2

技术细节清晰,有定量性能对比,来源为官方博客,内容质量高。

Practical value10 ×0.2

直接降低LLM部署门槛与成本,对AI工程化落地具有极高实用价值。

Timeliness10 ×0.15

发布即时,属于最新技术动态,时效性满分。

Source reliability9 ×0.15

来源为Hugging Face官方博客,vLLM为开源权威项目,可信度高。

Base 90.5 × T1 Source weight ×1 = 91

Curation line 60Selected

08:00Hugging Face:Blog(RSS)T1RSS

FeaturedvLLM Introduces Native-Speed Transformers Modeling Backend for Enhanced Inference Performance

vLLM推出原生速度Transformers建模后端,大幅提升推理性能

This update is critical for AI engineering teams: eliminating format conversion speeds up model iteration, and 2-5x speedup directly reduces GPU costs. If you're building LLM online services or batch inference, this is practically a must-read technical update.

AIModels#Hugging Face#PagedAttention#Transformers
90

Five-dimension score

Information gain9 ×0.3

手语转文本是AI无障碍领域的新突破,提供了此前罕见的具体模型信息。

Content quality8 ×0.2

来源权威,内容清晰描述了模型功能、应用场景和开发理念。

Practical value9 ×0.2

对聋人群体、开发者和无障碍研究者具有直接参考与应用价值。

Timeliness9 ×0.15

刚刚发布的官方公告,时效性非常高。

Source reliability10 ×0.15

Google DeepMind官方博客,信源可信度极高。

Base 89.5 × T1 Source weight ×1 = 90

Curation line 60Selected

22:01Google DeepMind:Blog(RSS)T1RSS

FeaturedGoogle DeepMind Introduces SL2T, a Sign Language-to-Text Model for Deaf Users

Google DeepMind 发布手语转文本模型 SL2T,助力聋人用户

This news matters not only as a technical breakthrough but also as a sign that AI is beginning to address the needs of marginalized groups. For developers, the architecture and technical approach of SL2T merit deep study; for accessibility advocates, it's a key case for advancing industry standards.

AIModels#Google DeepMind#SL2T#Sign Language Recognition

Verify against the original source before citing