Skip to content
Back

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

  1. Anthropic · Claude Code

    Claude Code 2.1.224

    7 new15 fixes9 other

    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. Added archive plugin source: install plugins from a zip over HTTPS without git or npm, with optional SHA-256 pinning.

  2. Anthropic · Claude API

    You can now set a budget on a Claude Managed Agents session: a hard cap on the session’s spend, priced at…

    A session that reaches its budget pauses with the budget_reached stop reason instead of starting new model requests; changing or removing the budget resumes it. Deployments accept the same budget and apply it to each session they start. You can now give a Claude Managed Agents session an advisor: a model at least as capable as the agent’s own that the session’s primary thread can consult mid-turn for strategic guidance. You can now control where model inference runs for a Claude Managed Agents agent. Claude Managed Agents sessions can now load skills from a GitHub repository.

  3. OpenAI · Codex app

    ChatGPT for iOS

    Improved task reconnection with visible progress while keeping existing tasks usable during connection checks. New tasks now preserve their first prompt and attachments while starting, preventing empty tasks that could not be reopened. Improved editing performance for long prompts. Voice conversations now follow your Background Conversations setting. Approvals and user-input requests now recover reliably after reconnecting, with cleaner approval details in the transcript. Fixed follow-up /goal prompts after completing a goal. Fixed task-list freezes, disappearing task titles, flashing thinking summaries, and transcript crashes.

  4. OpenAI · Codex CLI

    Codex CLI 0.147.0

    6 new6 fixes5 other

    Install portable Agent Plugins and search across local, personal, workspace, and remote plugin catalogs. Organize conversations into persistent, manually ordered sections and browse long transcripts incrementally.

  5. Google · Antigravity

    Vim modal editing mode, Vim-aware submission, print-mode slash-command enhancements, and various CLI and…

    Vim modal editing mode with Normal, Insert, Visual, and Visual Line modes, Vim-aware prompt submission, Vim editing in comment/diff views, print-mode slash-command and non-interactive enhancements, plugin configuration improvements, and fixes for command auto-approval, MCP servers, and autocomplete history.

  6. Google · Antigravity

    Faster long conversations, more reliable hooks and subagents

    Conversations with long histories now open faster, improved custom hooks and subagents behavior, and administrator policies for connected tool servers are applied correctly — plus a broad set of fixes across chat, comments and the file viewer.

  7. Google · Gemini CLI

    Gemini CLI 0.54.0

    3 new8 fixes5 other

    post comment before auto-closing issues. implement Firestore concurrency dual-locking and test ingestion utilities.

  8. Anthropic · Claude Code

    Claude Code 2.1.223

    3 new12 fixes4 other

    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 warning when workflow agents, forked skills, slash commands, or resumed background agents' requested subagent model is restricted and the parent model runs instead.

  9. Anthropic · Claude apps

    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.

  10. OpenAI · Codex app

    Codex app

    Performance improvements and bug fixes. Fixed an issue where typing in Find could edit the open code file. Preserved the selected model and thinking level when moving a chat to a worktree. Made search for @-mentions case-insensitive.

  11. Anthropic · Claude API

    Inference hooks are now in beta for Claude Enterprise organizations

    Point Claude at your organization’s AI security server, and each governed prompt across claude.ai, Cowork, and Claude Code is held for the server’s allow or deny verdict before inference proceeds. Requests are signed, failure handling is configurable, and every denial is recorded in the compliance Activity Feed. We’ve retired the Claude Opus 4.1 model (claude-opus-4-1-20250805).

  12. OpenAI · Codex CLI

    Codex CLI 0.146.1

    1 fix

    Apply safer automatic-review defaults for cyber-capable models and explain permission changes in the terminal interface.

  13. Anthropic · Claude Code

    Claude Code 2.1.222

    16 fixes5 other

    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 PreToolUse auto-allow hooks bypassing tool restrictions in background agent tasks (summaries, compaction, renames).

  14. Anthropic · Claude Code

    Claude Code 2.1.221

    4 new17 fixes18 other

    [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 Focus view" command. Added mode: "mask" for sandbox credential files on Linux and WSL — sandboxed commands read a sentinel copy (the whole file, or just the spans captured by an extract regex) while the sandbox proxy substitutes the real value on egress; on macOS file masking falls back to deny.

  15. OpenAI · Codex app

    Codex app

    Added source-folder shortcuts to the terminal for projects with more than one folder. Performance improvements and bug fixes. Fixed duplicate pinned chats in the sidebar. Kept other project folders available when repairing worktree setup.

  16. Google · Antigravity

    Prioritized inference tiers, real-time token usage streaming, and context-aware hook decorators

    The 0.1.10 release introduces support for Gemini Prioritized Inference service tiers, real-time token usage event streaming, stateful context-aware hook decorators, and explicit tool call correlation IDs across hook callbacks. It also standardizes default system instruction merging behavior, fixes WebSocket compaction events, and expands local Gemma model documentation.

  17. Anthropic · Claude API

    The Compliance API now returns transcripts of Cowork sessions started on claude.ai web or mobile, in beta…

    GET /v1/compliance/apps/sessions/remote lists sessions and GET /v1/compliance/apps/sessions/remote/{session_id}/messages returns one session’s transcript, using your existing Compliance Access Key with the read:compliance_user_data scope.

  18. Google · Antigravity

    Gemini Enterprise & WIF authentication, read-only.git sandbox rules, hook ordering improvements, and…

    Gemini Enterprise Business sign-in, Workforce Identity Federation (WIF) and Application Default Credentials (ADC) auth support, read-only.git sandbox access, hook ordering improvements, and fixes for subagent tree termination, --model / --effort flag resolution, and multi-select spacebar toggling.

  19. Anthropic · Claude API

    Dreams now supports Claude Opus 5

  20. xAI · Grok API

    Grok Bot

    Grok Bot is now available. Durable AI teammates that work on a persistent cloud computer, with messaging, approvals, connectors, and routines.

  21. xAI · Grok API

    Imagine image API updates

    Auto quality. The quality parameter on grok-imagine-image-2.0 now accepts auto, and the default when quality is omitted has moved from medium to auto. Auto currently uses low for image generation and medium for image editing.

  22. xAI · New modelAnnouncement

    Grok 4.6

    Grok 4.6, SpaceXSI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API. It has a 500k context window, text and image inputs with text-only output, and no text output limit. Pricing is $2 / $0.50 / $6 per 1M tokens (input / cached input / output) below 200k prompt tokens, and $4 / $1 / $12 above.

  23. Google · Gemini CLI

    Gemini CLI 0.53.1

    1 fix

    cherry-pick f47d6c6 to release/v0.53.0-pr-28566 [CONFLICTS].

  24. OpenAI · Codex app

    GPT-5.4 and GPT-5.4 mini retire from Codex on August 31

    On August 31, 2026, GPT-5.4 and GPT-5.4 mini will no longer be available in Codex for users signed in with ChatGPT. GPT-5.4 and GPT-5.4 mini will remain available on the OpenAI API and Codex sessions authenticated with an API key. Switch to their recommended replacements: Replace gpt-5.4 with gpt-5.6-terra (GPT-5.6 Terra). Replace gpt-5.4-mini with gpt-5.6-luna (GPT-5.6 Luna). Before the cutoff, update workspace defaults, saved model settings, managed configurations, custom agents, and scheduled tasks that use either model.

  25. OpenAI · Codex app

    Record & Replay expands to the EU, UK, and Switzerland

    Record & Replay is now available in the European Union, the United Kingdom, and Switzerland. On macOS, demonstrate a workflow and turn it into a reusable skill. Computer Use must also be available and enabled.

  26. DeepSeek · New model

    DeepSeek-V4-Flash Update

    The official release of the DeepSeek-V4-Flash API is now in public beta. The API calling method remains unchanged — simply set the model name to deepseek-v4-flash to use the latest version. Note 1: For the Code Agent tasks in the public benchmark sets, the official DeepSeek-V4-Flash was tested using the DeepSeek Harness minimal mode (to be released soon) as the framework, with the max effort level, topp=0.95, and temperature=1.0 Note 2: DSBench-FullStack is an internal full-stack development test set, and DSBench-Hard is an internal Coding Agent hard-problem test set

  27. Google · Antigravity

    Slash-command expansion in print mode, non-blocking MCP startup, session-wide permission memory, system temp…

    Added slash-command and skill expansion in print mode, non-blocking background MCP loading during interactive startup, session-scoped permission pattern recording, system temporary directory write grants, and stability fixes for stop/PostToolUse hooks, artifact viewer, and MCP authentication.

  28. Google · Antigravity

    Enterprise sign-in: Gemini Enterprise accounts and Workforce Identity Federation

    Added enterprise sign-in support for Gemini Enterprise user accounts (with admin controls) and Workforce Identity Federation via Advanced SSO.

  29. OpenAI · Codex app

    Browser upgrades, multi-repository review, and image editing

    The latest ChatGPT desktop app update makes browsing, reviewing code, and editing generated images faster and easier. Type in the built-in browser's address bar to revisit pages from your browsing history or search Google when there's no match. Manage your browsing history in Settings, and let ChatGPT search that history when a task needs to find a page you visited before. Use the Chrome extension to mention open tabs or bring highlighted page text into your side chat. Ask questions about any YouTube video in the Chrome extension and get answers in seconds. Right-click a webpage and select Ask ChatGPT. Learn more about the built-in browser and the Chrome extension. Review changes across repositories. Select Review to inspect diffs across those repositories without switching between separate review views. Open generated images in an expanded viewer, and switch between Focused view and Canvas view. Add comments across images, choose the ones you want, and send targeted edits without leaving your conversation. Learn more about image generation. Other improvements and bug fixes. Added a new "Activity view" in the sidebar to view which chats you engaged with recently and require attention. Click the bell or use Cmd / Ctrl + Opt + U to change to the new view. Updated browser settings to show only supported browsers. Improved Windows installation reliability when package file paths are long. Other performance and bug fixes.

  30. Google · Gemini API

    Deprecation announcement: The gemini-robotics-er-1.6-preview model will be shut down on August 31, 2026

    Deprecation announcement: The gemini-robotics-er-1.6-preview model will be shut down on August 31, 2026.