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.
Anthropic · Claude Code·
Bug fixes and reliability improvements.
Anthropic · Claude Code·Aug 8, 2026
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 workspace trust prompt to claude agents for untrusted directories, matching the behavior of claude.
Google · Gemini CLI·Aug 7, 2026
cherry-pick 56f9688 to release/v0.54.0-pr-28700 to patch version v0.54.0 and create version 0.54.1.
Anthropic · Claude Code·Aug 7, 2026
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.
Anthropic · Claude API·Aug 7, 2026
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.
OpenAI · Codex app·Aug 7, 2026
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.
Google · Antigravity·Aug 7, 2026
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.
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.
Google · Gemini CLI·Aug 6, 2026
post comment before auto-closing issues. implement Firestore concurrency dual-locking and test ingestion utilities.
Anthropic · Claude Code·Aug 6, 2026
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.
Anthropic · Claude apps·Aug 6, 2026
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.
Anthropic · Claude API·Aug 5, 2026
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).
Anthropic · Claude Code·Aug 4, 2026
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).
[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.
Google · Antigravity·Aug 4, 2026
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.
Anthropic · Claude API·Aug 3, 2026
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.
Google · Antigravity·Aug 3, 2026
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.
Anthropic · Claude API·Aug 1, 2026
xAI · Grok API·Aug 1, 2026
Grok Bot is now available. Durable AI teammates that work on a persistent cloud computer, with messaging, approvals, connectors, and routines.
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.
xAI · New model·Aug 1, 2026Announcement
Grok 4.6, SpaceXAI'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.
Google · Gemini CLI·Jul 31, 2026
cherry-pick f47d6c6 to release/v0.53.0-pr-28566 [CONFLICTS].
OpenAI · Codex app·Jul 31, 2026
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.
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.
DeepSeek · New model·Jul 31, 2026
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
Google · Antigravity·Jul 31, 2026
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.
Added enterprise sign-in support for Gemini Enterprise user accounts (with admin controls) and Workforce Identity Federation via Advanced SSO.
OpenAI · Codex app·Jul 30, 2026
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.
Google · Gemini API·Jul 30, 2026
Deprecation announcement: The gemini-robotics-er-1.6-preview model will be shut down on August 31, 2026.
Google · New model·Jul 30, 2026
Gemini Robotics ER 2 in public preview: Released two new embodied reasoning model endpoints for robotics: gemini-robotics-er-2-preview: Advanced spatial reasoning, agentic code execution, multi-step tool orchestration, video moment finding, progress classification, and multi-robot coordination. gemini-robotics-er-2-streaming-preview: Optimized for real-time text streaming using the Live API, enabling low-latency robot agents with bidirectional audio and video input. Both model endpoints accept text, image, video, and audio inputs and support function calling with blocking behavior for physical robot actions. To get started, see the Gemini Robotics ER overview. For real-time streaming use cases, see Robotics with streaming.