Updatespage 3 of 7
Claude product updates
209 articles
Claude Managed Agents sessions that run in a self-hosted sandbox can now attach
Claude Managed Agents sessions that run in a self-hosted sandbox can now attach memory stores. The Python, TypeScript, and Go SDK workers download each attached store into the sandbox at its mount_pat
You can now restrict which sites a Claude Managed Agents agent's web_search and
You can now restrict which sites a Claude Managed Agents agent's web_search and web_fetch tools can reach. Set allowed_domains or blocked_domains on the tool's entry in the agent_toolset_20260401 conf
The Files API is now generally available on the Claude API.
The Files API is now generally available on the Claude API. Requests to the /v1/files endpoints, and Messages API requests that reference an uploaded file, no longer require the files-api-2025-04-14 b
Claude Code 2.1.236
- Added `ANTHROPIC_DEFAULT_MODEL` environment variable: sets the model new sessions start on, while a `/model` pick still overrides it and persists across restarts (unlike `ANTHROPIC_MODEL`) - Added `
Claude Code 2.1.237
- Fixed prompt caching for sessions using an LLM gateway or custom base URL - Added a built-in "Concise" output style: Claude leads with results and skips preamble and narration, while doing the work
What Claude's Protein Design and Chemistry Analysis Experiments Showed (Anthropic Research)
Anthropic's research post shows Claude designing protein binders with above-industry success rates and analyzing chemistry lab data with lab-matching accuracy — early steps in drug discovery.
Claude Code 2.1.235
- Added an optional `spellcheck` setting that underlines misspelled words in the prompt input as you type, using your installed `aspell`, `hunspell`, or `ispell` - Fixed whole-prompt-cache invalidatio
Anthropic Extends 50% Increase to Claude Code Weekly Limits Through August 31
Anthropic's official X account @ClaudeDevs announced it is extending the 50% increase to Claude Code weekly limits through August 31. The company said it hopes to make the change permanent, but capacity may be tight in the coming weeks due to strong demand.
Do Worker Retraining Programs Actually Work? — Anthropic Research Summary
Anthropic reviewed 56 randomized US studies plus European evidence on job retraining programs. Average effects are modest, but employer-linked 'sector programs' stood out as far more effective.
Claude Code 2.1.234
- Added the optional `CLAUDE_CODE_PROJECT_DIR_NAME` environment variable: hosts that give each session its own config directory can choose a short name for the per-project transcript directory - Added
What Claude's New Riemann Zeta Research Result Really Means
Anthropic's unreleased research Claude raised a key Riemann zeta function bound from 41.6% to 67.2%. Here's what actually happened and what it means for Claude Code users.
Claude Code 2.1.233
- Added GitLab merge request URL support to the `--worktree` flag and the `claude agents` view (where MRs display as `!N`) - Added an opt-in `forward_user_identity` apps gateway setting on Anthropic u
Claude Code 2.1.232
- Subagent forking is now on by default: a `subagent_type: "fork"` subagent inherits the full conversation and prompt cache, and non-teammate agent spawns in interactive sessions now run in the backgr
Claude Code 2.1.231
- Fixed MCP OAuth sign-in failing with a redirect URI mismatch for servers that use a pre-registered OAuth client, such as Slack
Claude Code 2.1.229
- Documented `claude remote-control --continue` for resuming the most recent Remote Control session - Added server-supplied Claude Code hook support for self-hosted runner sessions, matching managed-e
Claude Code 2.1.228
- Fixed interactive sessions that could stop redrawing entirely, while the process kept running, after a rare internal layout error - Fixed `git` / Git Bash not being found on Windows when Claude Code
Claude Code 2.1.227
- Fixed feature flags being evaluated without the user's subscription tier when a session started with an expired login token, which could wrongly prompt Max plan users to enable usage credits for Fab
Claude Code 2.1.226
- Bug fixes and reliability improvements
Claude Code Makes Auto Mode the Default Permission Setting Starting Aug 14
According to Anthropic's official @ClaudeDevs account, auto mode will become the default permission mode for Claude Code Pro, Max, and Team users starting August 14. In testing, auto mode's separate classifier caught 89% of dangerous commands, versus 14% under manual approval.
Claude Code 2.1.225
- Added gateway spend-limit support to Claude Code's usage warning; the limit-reached message now names the cap, its reset time, and the operator's message (requires the gateway on 2.1.225) - Added a
Claude Code Sessions Can Now Message Each Other
Anthropic's official account @ClaudeDevs announced that Claude Code sessions can now message each other. Only a summary is sent — not full history or files — and the receiving session picks up the task mid-way.
Claude Code 2.1.224
- Added self-hosted environments: `claude self-hosted-runner` turns your own machines or containers into a place Claude Code web, mobile, and desktop sessions can run, on Team and Enterprise plans - A
Skill and plugin security scanning (beta)
Enterprise plans can now turn on skill and plugin security scanning to automatically check third-party skills and plugins for malicious content when someone uploads or edits them. For more information
Anthropic Posts Update on Capacity Incident: Stable But Not Fully Resolved
Anthropic's official X account, @ClaudeDevs, posted a follow-up update on a capacity incident. The company said restoration has progressed and things are currently stable, though not fully resolved. Further updates will be posted on the official status page if issues arise.
We've retired the Claude Opus 4.1 model (claude-opus-4-1-20250805).
We've retired the Claude Opus 4.1 model (claude-opus-4-1-20250805). All requests to this model will now return an error. We recommend upgrading to Claude Opus 5. Researchers can request ongoing access
Claude Code 2.1.223
- Added owner wildcard entries (`"owner/*"`) to the `strictKnownMarketplaces` and `blockedMarketplaces` managed settings for allowing or blocking all marketplace repos under a GitHub org - Added a war
Claude Code 2.1.222
- Fixed worktree-isolated sessions and their subagents being able to run destructive git commands against the main checkout; isolation now applies to file edits and Bash in every session type - Fixed
Claude Code 2.1.221
- [VSCode] Added Focus view: a chat-menu toggle that hides tool activity behind an expandable per-turn summary with a live running-tool indicator, toggled with `Ctrl+Alt+F` or the "Claude Code: Toggle
Anthropic Updates Roundup - 2026/07 (16 items)
A monthly roundup of 16 Anthropic updates in 2026/07
Claude Hit by Two Incidents in 24 Hours Due to Network Failures
Anthropic's official account @ClaudeDevs announced that two incidents over the past 24 hours caused elevated errors and reduced availability for some Claude users. Multiple separate network failures cut into serving capacity, and some requests failed while traffic was rerouted. The announcement did not disclose the specific cause or duration of the incidents.