AI posts
AI release notes
Anthropic's official release notes. Claude apps: the website, desktop and phone apps. Claude Code: Claude's coding assistant. Claude API: what developers use to build Claude into their own products.
Compiled by the Toolstash team · Updated
Claude Code
Claude Code 2.1.84
9 new14 fixes17 otherAdded PowerShell tool for Windows as an opt-in preview. Learn more at https://code.claude.com/docs/en/tools-reference#powershell-tool. Added ANTHROPIC_DEFAULT_{OPUS,SONNET,HAIKU}_MODEL_SUPPORTS env vars to override effort/thinking capability detection for pinned default models for 3p (Bedrock, Vertex, Foundry), and _MODEL_NAME/_DESCRIPTION to customize the /model picker label.
Claude Code
Claude Code 2.1.83
7 new32 fixes20 otherAdded managed-settings.d/ drop-in directory alongside managed-settings.json, letting separate teams deploy independent policy fragments that merge alphabetically. Added CwdChanged and FileChanged hook events for reactive environment management (e.g., direnv).
Claude apps
Interactive apps in Claude for iOS and Android
The Claude mobile app can now connect to fully interactive apps. Pull up live charts, sketch diagrams, and build shareable assets, all rendered visually right in your conversation.
Claude appsAnnouncement
Computer use research preview in Cowork and Claude Code + Dispatch improvements
Users on Pro and Max plans can give Claude access to computer use. Claude can open files, run dev tools, point, click, and navigate to what’s on your screen to perform tasks itself—with no setup required. Claude’s new computer use capability makes Dispatch even more helpful by allowing it to use your computer on your behalf while you’re away.
Claude Code
Claude Code 2.1.81
2 new17 fixes8 otherAdded --bare flag for scripted -p calls — skips hooks, LSP, plugin sync, and skill directory walks; requires ANTHROPIC_API_KEY or an apiKeyHelper via --settings (OAuth and keychain auth disabled); auto-memory fully disabled. Added --channels permission relay — channel servers that declare the permission capability can forward tool approval prompts to your phone.
Claude Code
Claude Code 2.1.80
5 new6 fixes6 otherAdded rate_limits field to statusline scripts for displaying Claude.ai rate limit usage (5-hour and 7-day windows with used_percentage and resets_at). Added source: 'settings' plugin marketplace source — declare plugin entries inline in settings.json.
Claude Code
Claude Code 2.1.79
3 new11 fixes4 otherAdded --console flag to claude auth login for Anthropic Console (API billing) authentication. Added "Show turn duration" toggle to the /config menu.
Claude API
We’ve added model capability fields to the Models API
GET /v1/models and GET /v1/models/{model_id} now return max_input_tokens, max_tokens, and a capabilities object. Query the API to discover what each model supports.
Claude Code
Claude Code 2.1.78
4 new19 fixes3 otherAdded StopFailure hook event that fires when the turn ends due to an API error (rate limit, auth failure, etc.). Added ${CLAUDE_PLUGIN_DATA} variable for plugin persistent state that survives plugin updates; /plugin uninstall prompts before deleting it.
Claude Code
Claude Code 2.1.77
1 new28 fixes15 otherAdded allowRead sandbox filesystem setting to re-allow read access within denyRead regions.
Claude apps
Control Cowork from your phone with a persistent thread (research preview for Pro/Max)
Users on Pro and Max plans can access a persistent agent thread via Claude Desktop or Claude for iOS/Android to manage tasks in Cowork. We're rolling this out to Max plans starting today, and Pro plans over the next two days.
Claude API
We’ve launched the display field for extended thinking, letting you omit thinking content from responses for…
Set thinking.display: "omitted" to receive thinking blocks with an empty thinking field and the signature preserved for multi-turn continuity. Billing is unchanged. Learn more in Controlling thinking display.
Claude Code
Claude Code 2.1.76
7 new20 fixes8 otherAdded MCP elicitation support — MCP servers can now request structured input mid-task via an interactive dialog (form fields or browser URL). Added new Elicitation and ElicitationResult hooks to intercept and override responses before they're sent back.
Claude Code
Claude Code 2.1.75
Claude API
The 1M token context window is out of beta for Claude Opus 4.6 and Sonnet 4.6, at standard pricing
Requests over 200k tokens work automatically for these models with no beta header required. The 1M token context window remains in beta for Claude Sonnet 4.5 and Sonnet 4. We’ve removed the dedicated 1M rate limits for all supported models. We’ve raised the media limit from 100 to 600 images or PDF pages for each request when using the 1M token context window.
Claude Code
Claude Code 2.1.74
2 new13 fixes2 otherAdded actionable suggestions to /context command — identifies context-heavy tools, memory bloat, and capacity warnings with specific optimization tips. Added autoMemoryDirectory setting to configure a custom directory for auto-memory storage.
Claude apps
Claude creates interactive charts, diagrams and visualizations
Claude can now create custom charts, diagrams and other visualizations in-line in its responses.
Claude Code
Claude Code 2.1.73
2 new16 fixes8 otherAdded modelOverrides setting to map model picker entries to custom provider model IDs (e.g. Bedrock inference profile ARNs). Added actionable guidance when OAuth login or connectivity checks fail due to SSL certificate errors (corporate proxies, NODE_EXTRA_CA_CERTS).
Claude apps
Work across Excel and PowerPoint, plus 2 more changes
We’ve improved our Claude for Excel and Claude for PowerPoint add-ins. They can now share the full context of your conversation, so every action Claude takes in one application is informed by everything that’s happened in the other. We also added support for skills in the add-ins, and the ability for Amazon Bedrock, Google Cloud’s Vertex AI, or Microsoft Foundry users to connect to them via an LLM gateway.
Claude Code
Claude Code 2.1.72
9 new32 fixes13 otherAdded w key in /copy to write the focused selection directly to a file, bypassing the clipboard (useful over SSH). Added optional description argument to /plan (e.g., /plan fix the auth bug) that enters plan mode and immediately starts.
Claude Code
Claude Code 2.1.71
4 new18 fixes6 otherAdded /loop command to run a prompt or slash command on a recurring interval (e.g. /loop 5m check the deploy). Added cron scheduling tools for recurring prompts within a session.
Claude Code
Claude Code 2.1.70
3 new20 fixes6 other[VSCode] Added spark icon in VS Code activity bar that lists all Claude Code sessions, with sessions opening as full editors. [VSCode] Added full markdown document view for plans in VS Code, with support for adding comments to provide feedback.
Claude Code
Claude Code 2.1.69
21 new58 fixes24 otherAdded the /claude-api skill for building applications with the Claude API and Anthropic SDK. Added Ctrl+U on an empty bash prompt (!) to exit bash mode, matching escape and backspace.
Claude Code
Claude Code 2.1.68
3 otherOpus 4.6 now defaults to medium effort for Max and Team subscribers. Medium effort works well for most tasks — it's the sweet spot between speed and thoroughness. You can change this anytime with /model. Re-introduced the "ultrathink" keyword to enable high effort for the next turn.
Claude Code
Claude Code 2.1.66
Claude apps
Memory for free users, plus 2 more changes
Memory from chat history is now available for all Claude users, including free users.
Claude Code
Claude Code 2.1.63
6 new17 fixes3 otherAdded /simplify and /batch bundled slash commands. Added ENABLE_CLAUDEAI_MCP_SERVERS=false env var to opt out from making claude.ai MCP servers available.
Claude Code
Claude Code 2.1.62
1 fixFixed prompt suggestion cache regression that reduced cache hit rates.
Claude Code
Claude Code 2.1.61
1 fixFixed concurrent writes corrupting config file on Windows.
Claude Code
Claude Code 2.1.59
1 new2 fixes4 otherAdded /copy command to show an interactive picker when code blocks are present, allowing selection of individual code blocks or the full response.