Claude Code v2.1.196 Released: Org Default Models, Security Enhancements, Background Job Reliability
Score
70Why selected
Feature-rich with many critical bug fixes, especially background job reliability and security model improvements, which have significant impact on real workflows but are not revolutionary.
AI commentary
「This release significantly improves enterprise-grade usability, security, and background stability of Claude Code, making large-scale code collaboration and automated tasks more reliable.」
Quick overview
Claude Code v2.1.196 brings several key updates: support for organization default models set by admins in the org console, clickable file attachments, and readable default session names. Security-wise, it prevents auto-running untrusted MCP servers from committed .mcp.json, showing pending approval for untrusted workspaces. Fixed background jobs being permanently deleted, improved session recovery and background agent reliability. Also optimized /code-review workflow reducing token usage by ~25%, and enabled streaming idle watchdog by default.
- New organization default model support (Org default/Role default) configurable by admins in the console
- Security enhancement: preventing auto-starting untrusted MCP servers from committed .mcp.json
- Fixed background jobs losing conversation permanently due to process restart
- Code review workflow merged five cleanup steps, reducing token usage by ~25%
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- Notifications You must be signed in to change notification settings
- Fork 21.9k
- Star 136k
v2.1.196
CompareChoose a tag to compare
Sorry, something went wrong.
Filter LoadingSorry, something went wrong.
Uh oh!
There was an error while loading. Please reload this page.
No results found
View all tags
ashwin-ant
released this
29 Jun 23:27
v2.1.196
c80896c
What's changed
- Added support for organization default models — admins set it in the org console; it shows as "Org default" (or "Role default") in
/modelwhen you haven't picked one yourself - Added readable default names for sessions at start, making them easier to identify and message
- Added clickable file attachments in chat — Cmd/Ctrl-click reveals the file in Finder/Explorer
- Security:
claude mcp list/getno longer spawn.mcp.jsonservers that a repo self-approved via a committed.claude/settings.json; untrusted workspaces show⏸ Pending approval - Fixed waking a background job permanently deleting its conversation and re-running the original prompt when the transcript probe misread a real transcript; the file is now set aside, never deleted
- Fixed the rate-limit warning flickering off and rate-limit telemetry being over-counted when multiple parallel requests were in flight at the moment a usage limit was hit
- Fixed duplicate recap lines after a background session's turn: a schema-rejected StructuredOutput attempt no longer renders alongside its retry
- Fixed PowerShell
git diff/git grep,egrep/fgrep, and quoted search patterns containing|being reported as failures when they exit 1, matching Bash behavior - Fixed multiple
claude agentsside panel issues: keyboard focus getting stuck when opening an agent, background jobs losing their subagent types on every open, and sessions showing incorrect status while actively running - Fixed
claude agents --dangerously-skip-permissionssilently falling back to auto mode instead of showing the bypass disclaimer and applying bypass mode to spawned agents - Fixed mid-turn crash recovery for Remote sessions — sessions interrupted by a server restart now auto-resume on the next worker
- Fixed sessions moved with
/cdreappearing in the old directory's resume list after a non-graceful exit when the old path contained special characters - Fixed
claude plugin validateskipping local plugins whose source is "." and stopping after the first error class - Fixed Esc Esc at an idle prompt not opening the rewind menu (regression); use Ctrl+C or Ctrl+X Ctrl+K to stop background agents
- Fixed MCP OAuth requesting the authorization server's full
scopes_supportedcatalog when no scope is specified, causinginvalid_scopefailures on GitLab self-hosted and other enterprise IdPs - Fixed
/contextshowing 0 tokens for all tool groups on Bedrock - Fixed
/deep-researchmisreporting verifier failures as "all claims refuted" instead ofunverified - Fixed plugin dependency version pins not being honored when the marketplace was added as a local folder path backed by a git repo
- Fixed
claude agentssession status: completed rows no longer flip between "Done" and "Needs your input", stalled agents are now labeled "Needs attention", and results that mention a PR show a clickable link - Fixed voice dictation swallowing spaces and spuriously starting a recording during very fast typing when voice mode is enabled
- Improved background session reliability: long-running commands and workflows now survive the session's process being stopped, restarted, or updated — including on Windows, where background shells are handed off instead of being killed
- Improved background agents: workers killed by a daemon restart are now automatically resumed from where they left off the next time the agents view opens
- Improved
/code-reviewworkflow: merged five cleanup finders into one, cutting token usage by roughly 25% - Reduced per-frame rendering work in the terminal UI by skipping no-op subtree walks during streaming
- The streaming idle watchdog is now on by default for all providers — it aborts and retries when a response stream produces no events for 5 minutes. Set
CLAUDE_ENABLE_STREAM_WATCHDOG=0to disable. - Remote Control is now disabled when
ANTHROPIC_BASE_URLpoints at a non-Anthropic host, matching the existing behavior underCLAUDE_CODE_USE_BEDROCK/_VERTEX/_FOUNDRY - Changed opening the agents view from a foreground session to require a single
←press instead of two, matching the behavior in background sessions
Uh oh!
There was an error while loading. Please reload this page.
👍 18 mike1858, raky291, eyoboue, saita08, LocShadowVN, WolfStackSolutions, htnabe, HaoYuToDo, itsandreramon, egoan82, and 8 more reacted with thumbs up emoji 😄 3 mike1858, saita08, and LocShadowVN reacted with laugh emoji 🎉 6 mike1858, saita08, thinh9e, LocShadowVN, JRAVILES, and Leftyx reacted with hooray emoji ❤️ 8 mike1858, saita08, LocShadowVN, JRAVILES, jsaristi, ainayves, aniketqxp, and DiamondKJ reacted with heart emoji 🚀 8 mike1858, saita08, LocShadowVN, JRAVILES, xxddpac, egoan82, mrverdant13, and DiamondKJ reacted with rocket emoji 👀 5 mike1858, saita08, LocShadowVN, fmendezy, and brandaltux reacted with eyes emoji All reactions- 👍 18 reactions
- 😄 3 reactions
- 🎉 6 reactions
- ❤️ 8 reactions
- 🚀 8 reactions
- 👀 5 reactions
Related items
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.
91
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.
91
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.
91
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.
91
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.
91
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.
91
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.
90
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.