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. DeepSeek · New model

    DeepSeek-V4

    The DeepSeek API now supports V4-Pro and V4-Flash, available via both the OpenAI ChatCompletions interface and the Anthropic interface. To access the new models, the base_url remains unchanged, and the model parameter should be set to deepseek-v4-pro or deepseek-v4-flash. The two legacy API model names, deepseek-chat and deepseek-reasoner, will be discontinued in three months (2026-07-24). During the current period, these two model names point to the non-thinking mode and thinking mode of deepseek-v4-flash, respectively.

  2. Anthropic · Claude Code

    Claude Code 2.1.119

    2 new32 fixes17 other

    Added prUrlTemplate setting to point the footer PR badge at a custom code-review URL instead of github.com. Added CLAUDE_CODE_HIDE_CWD environment variable to hide the working directory in the startup logo.

  3. Google · Gemini CLI

    Gemini CLI 0.39.0

    24 new35 fixes47 other

    add memory usage integration test harness. add /memory inbox command for reviewing extracted skills.

  4. Anthropic · Claude Code

    Claude Code 2.1.118

    4 new21 fixes9 other

    Added vim visual mode (v) and visual-line mode (V) with selection, operators, and visual feedback. Added DISABLE_UPDATES env var to completely block all update paths including manual claude update — stricter than DISABLE_AUTOUPDATER.

  5. Anthropic · Claude API

    Memory for Claude Managed Agents is now in beta under the standard managed-agents-2026-04-01 header

  6. OpenAI · New modelAnnouncement

    GPT-5.5 and Codex app updates

    GPT-5.5 is now available in Codex as OpenAI's newest frontier model for complex coding, computer use, knowledge work, and research workflows. GPT-5.5 in Codex. GPT-5.5 is the recommended choice for most Codex tasks when it appears in your model picker. It's especially useful for implementation, refactors, debugging, testing, validation, and knowledge-work artifacts. To switch to GPT-5.5: In the CLI, start a new thread with: bash codex --model gpt-5.5 Or use /model during a session. In the IDE extension, choose GPT-5.5 from the model selector in the composer. In the Codex app, choose GPT-5.5 from the model selector in the composer. If you don't see GPT-5.5 yet, update the CLI, IDE extension, or Codex app to the latest version. During the rollout, continue using GPT-5.4 if GPT-5.5 is not yet available. The Codex app can now let Codex operate the in-app browser for local development servers and file-backed pages. Ask Codex to use the browser when it needs to click through a rendered UI, reproduce a visual bug, or verify a local fix inside the app. Browser use runs through the bundled Browser plugin. In settings, you can manage the plugin and review allowed or blocked websites. Codex can route eligible approval prompts through an automatic reviewer agent before the request runs. When configured, the Codex app shows an automatic review item with the review status and risk level, so you can see whether the reviewer approved, denied, stopped, or timed out before deciding. Performance improvements and bug fixes. Fixed duplicate queued follow-up messages across app windows. Fixed new chats reverting to outdated model and thinking settings. Kept edits to the same file grouped together after reopening a chat.

  7. Anthropic · Claude Code

    Claude Code 2.1.117

    14 fixes14 other

    Forked subagents can now be enabled on external builds by setting CLAUDE_CODE_FORK_SUBAGENT=1. Agent frontmatter mcpServers are now loaded for main-thread agent sessions via --agent.

  8. Google · Gemini API

    Released gemini-embedding-2 as generally available. To learn more, see the Embeddings page

    Released gemini-embedding-2 as generally available (GA). To learn more, see the Embeddings page.

  9. Google · Gemini API

    Released new versions of the Deep Research agent with collaborative planning, visualization support, MCP…

    Released new versions of the Deep Research agent with collaborative planning, visualization support, MCP server integration, and File Search: deep-research-preview-04-2026: Designed for speed and efficiency, ideal to be streamed back to a client UI. deep-research-max-preview-04-2026: Maximum comprehensiveness for automated context gathering and synthesis.

  10. Anthropic · Claude Code

    Claude Code 2.1.116

    12 fixes12 other

    /resume on large sessions is significantly faster (up to 67% on 40MB+ sessions) and handles sessions with many dead-fork entries more efficiently. Faster MCP startup when multiple stdio servers are configured; resources/templates/list is now deferred to first @-mention.

  11. Anthropic · Claude API

    We’ve retired the Claude Haiku 3 model

    All requests to this model will now return an error. We recommend upgrading to Claude Haiku 4.5.

  12. OpenAI · Codex app

    Codex app

    Added local branch search and non-image file pasting in the composer. Added collapsible sidebar sections, tray usage-limit surfacing, and a command-palette theme switcher. Performance improvements and bug fixes. Made review faster and more stable with better diff batching and preserved diff and search state. Fixed projectless cwd and permissions handling, default file opening, spreadsheet suggestions, and remote-control reconnect issues. Additional performance improvements and bug fixes.

  13. Anthropic · Claude Code

    Claude Code 2.1.114

    1 fix

    Fixed a crash in the permission dialog when an agent teams teammate requested tool permission.

  14. Anthropic · Claude Code

    Claude Code 2.1.113

    1 new22 fixes15 other

    Added sandbox.network.deniedDomains setting to block specific domains even when a broader allowedDomains wildcard would otherwise permit them.

  15. Google · Gemini CLI

    Gemini CLI 0.38.2

    1 fix

    cherry-pick 14b2f35 to release/v0.38.1-pr-24974 to patch version v0.38.1 and create version 0.38.2.

  16. Anthropic · Claude appsAnnouncement

    Claude Design by Anthropic Labs

    With Opus 4.7, we also launched Claude Design, a new Anthropic Labs product that lets you collaborate with Claude to create visual outputs like designs, prototypes, slides, and one-pagers.

  17. Anthropic · Claude Code

    Claude Code 2.1.112

    1 fix

    Fixed "claude-opus-4-7 is temporarily unavailable" for auto mode.

  18. Anthropic · Claude Code

    Claude Code 2.1.111

    5 new10 fixes20 other

    Added xhigh effort level for Opus 4.7, sitting between high and max. Available via /effort, --effort, and the model picker; other models fall back to high. Added "Auto (match terminal)" theme option that matches your terminal's dark/light mode — select it from /theme.

  19. Anthropic · Claude API

    We’ve launched Claude Opus 4.7, our most capable model for complex reasoning and agentic coding, at the same…

    Opus 4.7 includes API breaking changes versus Opus 4.6; see the migration guide before upgrading. Claude in Amazon Bedrock is now open to all Amazon Bedrock customers. We’ve launched task budgets in beta on Claude Opus 4.7. Claude Opus 4.7 supports high-resolution image input, raising the maximum image resolution from 1568 to 2576 pixels on the long edge for improved performance on computer use, screenshot understanding, and document analysis. We’ve added the xhigh effort level on Claude Opus 4.7. xhigh sits between high and max and is tuned for long-running agentic and coding tasks (over 30 minutes) with token budgets in the millions.

  20. Anthropic · Claude appsAnnouncement

    Claude Opus 4.7 launch

    Our latest model, Claude Opus 4.7, is now generally available. Opus 4.7 shows improvements in software engineering and complex, long-running coding tasks, as well as better vision, allowing it to see images in higher resolution.

  21. OpenAI · Codex app

    Codex can now help with more of your work

    Codex is becoming a broader workspace for getting work done with AI. This update makes it easier to start work with less setup, verify what Codex is building, create richer outputs, and keep momentum across longer-running tasks. The Codex app now includes an early in-app browser. You can open local or public pages that don't require sign-in, comment directly on the rendered page, and ask Codex to address page-level feedback. !Codex app showing a browser comment on a local web app preview. Computer use lets Codex operate macOS apps by seeing, clicking, and typing, which helps with native app testing, simulator flows, low-risk app settings, and GUI-only bugs. The feature isn't available in the European Economic Area, the United Kingdom, or Switzerland at launch. Start, follow, and steer work. Chats are threads you can start without choosing a project folder first. They're useful for research, writing, planning, analysis, source gathering, and tool-driven work that doesn't begin in a codebase. For work that needs a later check-in, thread automations can wake up the same thread on a schedule while preserving the conversation context. Use them to check a long-running process, watch for updates, or continue a follow-up loop without starting from scratch. The task sidebar makes plans, sources, generated artifacts, and summaries easier to follow while Codex works. Context-aware suggestions can also help you pick up relevant follow-ups when you start or return to Codex. Stronger for software development. Codex now brings more of the pull request workflow into the app. You can inspect GitHub pull requests in the sidebar, review comments in the diff, review changed files, then ask Codex to explain feedback, make changes, check them, and keep the review moving. The artifact viewer can preview generated files such as PDF files, spreadsheets, documents, and presentations in the sidebar before you commit or share them. Memories, where available, can also carry useful context from past tasks into future threads, including stable preferences, project conventions, and recurring work patterns. Remote connections - We're gradually rolling out SSH remote connections in alpha. Support for multiple terminals. macOS menu bar and Windows system tray support. Multi-window support. Intel Mac support. New plugins. Improved thread and tool rendering.

  22. Google · Antigravity

    Bug Fixes

    Fixed bug that prevented MCP servers from loading and bug that prevented accessing workspace-specific settings.

  23. Anthropic · Claude Code

    Claude Code 2.1.110

    4 new19 fixes10 other

    Added /tui command and tui setting — run /tui fullscreen to switch to flicker-free rendering in the same conversation. Added push notification tool — Claude can send mobile push notifications when Remote Control and "Push when Claude decides" config are enabled.

  24. Google · Gemini CLI

    Gemini CLI 0.38.1

    1 fix

    cherry-pick 050c303 to release/v0.38.0-pr-25317 to patch version v0.38.0 and create version 0.38.1.

  25. Anthropic · Claude Code

    Claude Code 2.1.109

    1 other

    Improved the extended-thinking indicator with a rotating progress hint.

  26. Google · Gemini API

    Launched Gemini 3.1 Flash TTS Preview, our cost-efficient, expressive, and steerable text to speech model.…

    Launched Gemini 3.1 Flash TTS Preview, our cost-efficient, expressive, and steerable text to speech model. Read the Text-to-Speech docs to learn more.

  27. Google · Gemini app

    Meet your new desktop assistant: Gemini for Mac

    What: We’re introducing the Gemini app for Mac, a native desktop experience built to help you get more done without disrupting your flow. With a simple keyboard shortcut (Option + Space), you can bring up Gemini alongside any application you're using. You can also seamlessly share your window, allowing Gemini to understand your context and assist with exactly what’s on your screen. The new desktop app is available to users on macOS versions 15 and up, globally, for free. Download the app directly at gemini.google/desktop. Why: By bringing a native app to Mac, we're cutting down on context switching and giving you a faster, more integrated way to use Gemini alongside the tools you use every day.

  28. Google · Gemini CLI

    Gemini CLI 0.38.0

    25 new38 fixes47 other

    explicitly allow web_fetch in plan mode with ask_user. add experimental.adk.agentSessionNoninteractiveEnabled setting.

  29. Anthropic · Claude Code

    Claude Code 2.1.108

    4 new14 fixes6 other

    Added ENABLE_PROMPT_CACHING_1H env var to opt into 1-hour prompt cache TTL on API key, Bedrock, Vertex, and Foundry (ENABLE_PROMPT_CACHING_1H_BEDROCK is deprecated but still honored), and FORCE_PROMPT_CACHING_5M to force 5-minute TTL. Added recap feature to provide context when returning to a session, configurable in /config and manually invocable with /recap; force with CLAUDE_CODE_ENABLE_AWAY_SUMMARY if telemetry disabled.

  30. Anthropic · Claude Code

    Claude Code 2.1.107

    1 other

    Show thinking hints sooner during long operations.