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 apps

    A new way to reflect with Claude

    Your monthly recap is a new feature at Settings > Reflect that shows you the topics you spent time on, your most active day and peak hour, and observations about how you work with Claude. It's in beta on Free, Pro, and Max plans on the web and Claude Desktop, and requires memory to be on. Alongside it, Settings > Time and focus lets you set optional break reminders and quiet hours.

  2. OpenAI · Codex app

    Codex joins the ChatGPT desktop app

    Codex is now part of the ChatGPT desktop app on macOS and Windows. Existing Codex app users can update as usual and keep their projects, settings, and workflows. You can make Codex the default view and, on macOS, keep the Codex app icon. Edit Markdown and code directly in the app, use inline annotations, and ask Codex to revise selected content. Use PR Chat to review GitHub pull requests and ask Codex about changes in context. Send inline review feedback, inspect proposed patches, and edit, accept, or reject them without leaving the app. Connect custom domains to published Sites. Performance improvements and bug fixes. Made Computer Use faster with GPT-5.6. Made task and subagent activity easier to follow while Codex works. Simplified plugin management by moving it into Settings. Improved permission handling when resuming tasks or sending follow-ups. Added clearer Full access warnings and a dialog when combining Full access with Ultra. Improved macOS and Windows setup, including macOS installation, Git-backed workflows, and Computer Use on Windows. Fixed task resumption for local projects and onboarding retry loops. Fixed scrolling in pull request reviews and expanded Mermaid diagram labels. Improved mobile connection reliability and fixed video rendering for SSH projects. Additional performance improvements and bug fixes.

  3. OpenAI · Codex CLI

    Codex CLI 0.144.0

    6 new6 fixes5 other

    Usage-limit reset credits now show their type and expiration, and let you choose which credit to redeem. Added a writes app-approval mode that allows declared read-only actions while prompting for writes.

  4. OpenAI · Codex CLI

    Codex CLI 0.144.1

    3 fixes

    Fixed standalone installs failing when GitHub returns compact or reordered release metadata. Ensured macOS package installs expose the code-mode host alongside the codex executable.

  5. Google · Antigravity

    LiteRT model configurations, dynamic GCP environment hydration, and performance updates

    This release expands local execution capabilities by broadening support for multimodal and web-connected tool workflows. Developers can now run Gemma models locally using LiteRT or integrate with local OpenAI-compatible APIs, natively return multimodal media from custom tools, and leverage a more robust, streamlined lifecycle hooks framework that is fully aligned with Model Context Protocol (MCP) workflows.

  6. Meta · Llama API

    Introducing Muse Spark 1.1

    Introducing Muse Spark 1.1

  7. Anthropic · Claude Code

    Claude Code 2.1.205

    1 new15 fixes7 other

    Added an auto mode rule that blocks tampering with session transcript files.

  8. Google · Gemini CLI

    Gemini CLI 0.50.0

    2 fixes2 other

    prevent workspace binary shadowing in release verification. prevent bad NPM releases and promote job crashes.

  9. Anthropic · Claude Code

    Claude Code 2.1.204

    1 fix

    Fixed hook events not streaming during SessionStart hooks in headless sessions, which could cause remote workers to be idle-reaped mid-hook.

  10. Anthropic · Claude API

    You can now set an expiration when you create an API key or an Admin API key in the Claude Console

    Choose a preset, a custom duration, or Never. For keys with a lifetime of at least 7 days, Anthropic emails the creator before expiration. Existing keys are unaffected. The Admin API reports each key’s expiration in the expires_at field.

  11. OpenAI · Codex CLI

    Codex CLI 0.143.0

    6 new6 fixes2 other

    Remote plugins are now enabled by default, with richer catalog rows, npm marketplace sources, and visible remote/local versions. Codex can route authentication and Responses API traffic through macOS and Windows system proxies, including PAC and WPAD configurations.

  12. Google · Antigravity

    Request-review mode, execution mode cycling, and line-level diff previews

    Public release of mode cycling, default request-review mode with interactive line-level diff previews, and settings panel integration.

  13. Anthropic · Claude Code

    Claude Code 2.1.203

    4 new26 fixes7 other

    Added a warning when your login is about to expire, so you can re-authenticate before background sessions are interrupted. Added a grey ⏸ badge to the footer when in manual permission mode, making the active mode always visible.

  14. Anthropic · Claude apps

    Claude Cowork on web and mobile, plus 1 more change

    Claude Cowork is now available on web and mobile in addition to desktop. We are rolling this capability out over the next several weeks starting with the Max plan, with more plans to follow. Cowork runs your sessions remotely (in beta), so your sessions and files are saved to your Claude account and go where you go, on any device. Work continues when you close your laptop, and scheduled tasks run with no device online. Chat and Cowork also share one home now, with one place for your projects and artifacts across both. The Microsoft 365 connector now goes beyond search. With write tools enabled, Claude can draft, send, and organize email, manage calendar events, update mailbox settings, and create and update files in OneDrive and SharePoint. Read and search tools work as before, and Teams remains read-only. Before members can use write tools, a Microsoft Entra administrator needs to consent to the updated permission set and an admin needs to enable them for the organization.

  15. Meta · Meta AI

    Introducing Muse Image and Muse Video

    Muse Image follows instructions faithfully, edits with precision, composes from multiple references, and draws on Instagram for social context. Muse Video delivers exceptional visual fidelity with native audio support.

  16. Anthropic · Claude Code

    Claude Code 2.1.202

    2 new13 fixes3 other

    Added a "Dynamic workflow size" setting in /config for controlling how large Claude generally makes dynamic workflows (small/medium/large agent counts) — an advisory guideline, not an enforced cap. Added workflow.run_id and workflow.name OpenTelemetry attributes to telemetry emitted by workflow-spawned agents, so a workflow run's activity can be reconstructed from OTel data.

  17. OpenAI · Codex app

    ChatGPT for iOS

    Added support for creating, searching, opening, forking, and managing Codex tasks directly from a conversation. Added filters for staged, unstaged, branch, and last-turn changes, with controls for comparing branches. Added support for adding selected transcript text directly to the composer. Added previews for image and file attachments before sending. Added inline Photos and Camera pickers to the attachment menu. Added a connection shortcut and support for SSH hosts using private keys or no credentials. Added usage limits and credit details to the task menu. Improved the task list with consistent task terminology, clearer delegated task titles, and a Needs input status. Improved initial task loading and foreground recovery. Improved autocomplete by selecting the first result automatically and accepting it with Return. Improved model, reasoning, and Fast settings so changes remain scoped to the current task. Improved task-management and dynamic tool activity presentation. Improved side chats to open directly when only one conversation is available. Improved plugin autocomplete with installed plugins and their icons. Improved workspace diff accuracy and expand-and-collapse navigation. Improved recovery by preserving thread state across reconnects and host pairings across sign-out. Fixed stuck thread-list loading, prompt mode deadlocks, stale images, and microphone permission alerts. Fixed shake to undo and keyboard refocusing after sending a prompt.

  18. Google · Gemini API

    Developer logs support for the Interactions API: logs for supported Interactions API calls are now viewable…

    Developer logs support for the Interactions API: logs for supported Interactions API calls are now viewable in the AI Studio dashboard.

  19. Anthropic · Claude Code

    Claude Code 2.1.201

    1 other

    Claude Sonnet 5 sessions no longer use the mid-conversation system role for harness reminders.

  20. Anthropic · Claude Code

    Claude Code 2.1.200

    13 fixes4 other

    Changed AskUserQuestion dialogs to no longer auto-continue by default; opt into an idle timeout via /config. Changed the "default" permission mode to "Manual" across the CLI, --help, VS Code, and JetBrains; --permission-mode manual and "defaultMode": "manual" are accepted alongside default.

  21. Anthropic · Claude Code

    Claude Code 2.1.199

    20 fixes4 other

    Stacked slash-skill invocations like /skill-a /skill-b do XYZ now load all leading skills (up to 5), not just the first. Fixed SSL certificate errors (TLS-inspecting proxies, missing NODE_EXTRA_CA_CERTS, expired certs) burning retries before showing actionable guidance — they now fail immediately with the fix hint.

  22. Anthropic · Claude API

    We’ve added the agent-memory-2026-07-22 beta header, which changes how listing memories behaves: results are…

    Page cursors issued without the header aren’t valid with it, so restart from the first page when you adopt it. On memory store endpoints, agent-memory-2026-07-22 replaces managed-agents-2026-04-01; sending both returns a 400 error. On July 22, 2026, the managed-agents-2026-04-01 header adopts the same list behavior. The Python (0.116.0), TypeScript (0.110.0), Go (1.56.0), Java (2.48.0), Ruby (1.55.0), PHP (0.36.0), C# (12.35.0), and CLI (1.16.0) SDKs now send agent-memory-2026-07-22 on all memory store calls instead of managed-agents-2026-04-01.

  23. Google · Antigravity

    Streaming task logs, model generation retries, and markdown subagents

    Auto-scrolling background task logs, automatic client-side generation retries, and markdown-based dynamic subagents.

  24. Anthropic · Claude Code

    Claude Code 2.1.198

    3 new18 fixes12 other

    Added background agent notifications in claude agents — sessions that need input or finish now fire the Notification hook (agent_needs_input / agent_completed). Added /dataviz skill for chart and dashboard design guidance with a runnable color-palette validator.

  25. Anthropic · Claude API

    We’ve restored access to Claude Fable 5 and Claude Mythos 5

  26. Anthropic · Claude appsAnnouncement

    Model entitlements for Enterprise plans (beta)

    Access to Claude Fable 5 and Claude Mythos 5 restored We are restoring access to Claude Fable 5 and Claude Mythos 5. Admins on Enterprise plans can now control what models their users have access to, and what effort level settings they can use.

  27. OpenAI · Codex CLI

    Codex CLI 0.142.5

    1 fix

    Prevented full Responses WebSocket request payloads from being written to trace logs.

  28. Google · Antigravity

    Subagent & task status bar, editor warnings, and Windows fixes

    New interactive status bar for subagents and background tasks, clipboard image pasting improvements, and Windows fixes.

  29. xAI · Grok API

    Adjustable VAD threshold for Speech to Text

    Speech to Text now accepts a vad_threshold parameter (streaming query param and batch multipart field) to tune the voice-activity gate that skips non-speech audio. Lower values transcribe quieter or noisier speech — useful for narrowband telephony — and 0 disables the gate.

  30. xAI · New modelAnnouncement

    Grok 4.5

    Grok 4.5, SpaceXSI's model for coding, agentic tasks, and knowledge work, is now available on the xAI API. Priced at $2 / 1M input tokens and $6 / 1M output tokens, with configurable reasoning effort (low, medium, or high; default high).