AI posts
AI release notes
Official updates from Anthropic, OpenAI, Google, xAI, Mistral, DeepSeek and Meta, newest first. Open any update for a short AI summary and the full notes.
Compiled by the Toolstash team · Updated
Anthropic · Claude API
MCP tunnels is now available as a research preview, so you can connect to MCP servers in your private network
Self-hosted sandboxes are now available for Claude Managed Agents, as an alternative to running tool execution in Anthropic’s infrastructure. With Claude Managed Agents, you can now update the agent’s MCP server and tool configurations associated with an active session. With Claude Managed Agents, large outputs from agent_toolset and MCP tools exceeding 100K characters (about 25K tokens) are now automatically spilled to a file in the sandbox.
Google · Gemini API
Released gemini-3.5-flash, the generally available version of Gemini 3.5 Flash, our most intelligent model…
Released gemini-3.5-flash, the generally available (GA) version of Gemini 3.5 Flash, our most intelligent model for sustained frontier performance on agentic and coding tasks. This is now the model behind gemini-flash-latest. Launched the Managed Agents in the Gemini API in public preview. This enables developers to build and deploy autonomous, stateful agents that run in secure, isolated Google-hosted Linux sandbox environments. To learn more, see the Agents overview page and the Quickstart. Released the general-purpose Antigravity Agent managed agent, antigravity-preview-05-2026, in public preview. The Antigravity agent can autonomously plan, reason, write and execute code, manage files, and browse the web inside its sandbox container.
Google · Gemini app
Gemini Spark is your 24/7 personal AI agent, plus 7 more changes
What: Gemini Spark introduces a whole new way to get things done. It helps you navigate your digital life by working on your tasks on your behalf. Gemini Spark is rolling out today to trusted testers and in Beta to Google AI Ultra subscribers aged 18 and over in the United States in the coming weeks. You can access Gemini Spark by tapping on the Spark tab in your Gemini app menu. Why: With Gemini Spark, we are transforming Gemini from an AI assistant that answers your questions into one that actually works proactively on your behalf.
Google · Antigravity
AGY 2.0 Bug Fixes
Antigravity 2.0 Launch bug fixes.
Google · Antigravity
First Release
The first release of the Antigravity IDE.
Anthropic · Claude API
The web search tool now returns richer SEC filing data, making it easier to ground financial research…
OpenAI · Codex app
ChatGPT for iOS
Added support for opening completed Codex tasks directly from iOS notifications. Added the ability to open changed files directly while reviewing a task. Improved task resume, reconnection, and foreground reliability. Improved task progress updates, code review, and message composition.
Anthropic · Claude Code
Claude Code 2.1.143
3 new16 fixes14 otherAdded plugin dependency enforcement: claude plugin disable now refuses when another enabled plugin depends on the target (with a copy-pasteable disable-chain hint), and claude plugin enable force-enables transitive dependencies. Added projected context cost (per-turn and per-invocation token estimates) to the /plugin marketplace browse pane.
Anthropic · Claude Code
Claude Code 2.1.142
1 new16 fixes7 otherAdded new claude agents flags: --add-dir, --settings, --mcp-config, --plugin-dir, --permission-mode, --model, --effort, and --dangerously-skip-permissions to configure dispatched background sessions.
OpenAI · Codex app
Work with Codex from anywhere
You can now use Codex from the ChatGPT mobile app by connecting it to a Mac running the Codex app. Codex runs from the connected host, so the same projects, files, credentials, plugins, skills, and configuration are available from your phone. This launch also includes Hooks general availability, Codex access tokens for trusted automation, and Enterprise admin setup guidance.
Anthropic · Claude Code
Claude Code 2.1.141
4 new44 fixes13 otherAdded terminalSequence field to hook JSON output so hooks can emit desktop notifications, window titles, and bells without a controlling terminal. Added CLAUDE_CODE_PLUGIN_PREFER_HTTPS to clone GitHub plugin sources over HTTPS instead of SSH, for environments without a GitHub SSH key.
Anthropic · Claude API
We’ve launched cache diagnostics in beta
Pass diagnostics.previous_message_id on a Messages request and the API reports a cache_miss_reason explaining where the prompt cache prefix diverged from the previous turn. Include the cache-diagnosis-2026-04-07 beta header in your requests.
Google · Gemini CLI
Gemini CLI 0.42.0
15 new53 fixes53 otheradd --delete flag to /exit command for session deletion. added microphone and updated placeholder for voice mode.
Anthropic · Claude Code
Claude Code 2.1.140
10 fixes3 otherImproved Agent tool subagent_type matching to accept case- and separator-insensitive values (e.g. "Code Reviewer" resolves to code-reviewer). Updated agent color palette.
Anthropic · Claude API
Fast mode now supports Claude Opus 4.7
Set speed: "fast" with model: "claude-opus-4-7" and the fast-mode-2026-02-01 beta header for significantly faster output token generation at premium pricing. Pricing, rate limits, and access are the same as for Opus 4.6 fast mode; interested customers should join the waitlist.
Anthropic · Claude Code
Claude Code 2.1.139
7 new32 fixes11 otherAdded agent view (Research Preview): a single list of every Claude Code session — running, blocked on you, or done. Run claude agents to get started. See https://code.claude.com/docs/en/agent-view. Added /goal command: set a completion condition and Claude keeps working across turns until it's met. Works in interactive, -p, and Remote Control. Shows live elapsed/turns/tokens as an overlay panel.
Anthropic · New model
New model: Claude Platform on AWS
We’ve launched Claude Platform on AWS, bringing the Claude API to Anthropic-managed infrastructure accessible through AWS, with AWS billing and IAM authentication. Access the full Messages API, Files API, Message Batches API, Claude Managed Agents, Agent Skills, code execution, and tool use through native AWS endpoints. Learn more in Claude Platform on AWS.
OpenAI · Codex app
Expanded Auto-review documentation
Added a dedicated Auto-review page covering the reviewer lifecycle, trigger conditions, failure behavior, and local or managed configuration. Also updated the Agent approvals & security and Sandbox docs so they explain more clearly how Auto-review relates to the sandbox boundary.
Anthropic · Claude Code
Claude Code 2.1.138
1 otherInternal fixes.
Anthropic · Claude Code
Claude Code 2.1.137
1 fix[VSCode] Fixed extension failing to activate on Windows.
Anthropic · Claude Code
Claude Code 2.1.136
2 new46 fixes4 otherAdded CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL to re-enable the session quality survey for enterprises capturing responses through OpenTelemetry. Added settings.autoMode.hard_deny for auto mode classifier rules that block unconditionally regardless of user intent or allow exceptions.
OpenAI · Codex app
Codex app
Added an in-app trust review flow for hooks and kept Hooks settings reachable even before hooks are fully configured. Performance improvements and bug fixes. Restored tooltip-wrapped dropdowns that could stop opening after the tooltip rewrite. Preserved in-progress message edits across thread switches. Fixed several desktop workflow regressions, including Ctrl+V paste in the Windows terminal, opening modified external links outside the in-app browser, and keeping feedback slash commands attached to the right thread. Improved loading and panel polish by showing model loading while a thread resumes, hiding unavailable model controls during load, and bundling summary-panel layout and hover fixes. Kept the Computer Use settings control visible even when uninstalled and disabled problematic extension hover panels. Additional performance improvements and bug fixes.
Anthropic · Claude Code
Claude Code 2.1.133
3 new10 fixes4 otherAdded worktree.baseRef setting (fresh | head) to choose whether --worktree, EnterWorktree, and agent-isolation worktrees branch from origin/ or local HEAD. Note: the default fresh changes EnterWorktree's base back to origin/ (it has been local HEAD since 2.1.128) — set worktree.baseRef: "head" to keep unpushed commits in new worktrees. Added sandbox.bwrapPath and sandbox.socatPath managed settings (Linux/WSL) to specify custom bubblewrap and socat binary locations.
OpenAI · Codex app
Codex for Chrome
With the new extension for Chrome, Codex is even better at working with apps and websites in your browser. It works in parallel across tabs in the background without taking over your browser, and you stay in control of which websites Codex can use. Learn more in the Codex Chrome extension documentation.
Google · Gemini API
Released gemini-3.1-flash-lite, the generally available version of Gemini 3.1 Flash-Lite, optimized for…
Released gemini-3.1-flash-lite, the generally available (GA) version of Gemini 3.1 Flash-Lite, optimized for speed, scale, and cost efficiency. Deprecation announcement: The gemini-3.1-flash-lite-preview model is deprecating on 5/11/26 and will be shut down on May 25, 2026.
Anthropic · Claude Code
Claude Code 2.1.132
3 new23 fixes2 otherAdded CLAUDE_CODE_SESSION_ID environment variable to the Bash tool subprocess environment, matching the session_id passed to hooks. Added CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1 env var to opt out of the fullscreen alternate-screen renderer and keep the conversation in the terminal's native scrollback.
Google · Gemini CLI
Gemini CLI 0.41.2
1 fixcherry-pick 02995ba to release/v0.41.1-pr-26568 to patch version v0.41.1 and create version 0.41.2.
Anthropic · Claude Code
Claude Code 2.1.131
2 fixesFixed VS Code extension failing to activate on Windows due to a hardcoded build path in the bundled SDK (createRequire polyfill bug). Fixed Mantle endpoint authentication failing with missing x-api-key header.
Anthropic · Claude Code
Claude Code 2.1.129
3 new17 fixes7 otherAdded --plugin-url flag to fetch a plugin .zip archive from a URL for the current session. Added CLAUDE_CODE_FORCE_SYNC_OUTPUT=1 env var to force-enable synchronized output on terminals that auto-detection misses (e.g. Emacs eat).
Anthropic · Claude API
Multiagent orchestration and Outcomes are now in beta under the standard managed-agents-2026-04-01 beta header
Claude Managed Agents vault credential background refresh is now supported for mcp_oauth credentials. Webhooks for Claude Managed Agents are now supported. Additional filtering and sorting options are now supported for Claude Managed Agents. Dreams for Claude Managed Agents are now available as a research preview.