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 2.1.214

    7 new35 fixes5 other

    Added the EndConversation tool: Claude can end sessions with highly abusive users or jailbreak attempts, as on claude.ai since 2025 — see https://www.anthropic.com/research/end-subset-conversations. Added a periodic progress heartbeat for long-running tool calls that previously went silent.

  2. OpenAI · Codex CLI

    Codex CLI 0.144.6

    1 fix

    Refreshed bundled instructions for GPT-5.6 Sol, Terra, and Luna, and corrected their context windows to 272,000 tokens.

  3. Google · Antigravity

    Slash command chaining, diff scrolling fixes, and headless policy enforcement

    Added slash command stacking (chaining multiple commands in a single prompt), diff viewer scroll fixes, headless mode settings.json policy enforcement, and subagent declaration fixes.

  4. Anthropic · Claude Code

    Claude Code 2.1.212

    3 new28 fixes17 other

    Added claude auto-mode reset to restore the default auto-mode configuration, with a confirmation prompt (pass --yes to skip). Added a session-wide limit on WebSearch tool calls (default 200, tunable via CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION) to stop runaway search loops.

  5. Anthropic · Claude API

    The legacy Workbench in the Claude Console is being sunset with access ending on August 17, 2026

    Saved prompts, variables, and evals are not supported in the updated Workbench in the Console. You can export any data you want to keep from the banner and under your Organizational Settings. For more, see How do I use the Workbench? in the Claude Help Center. The experimental prompt tools APIs for generating, improving, and templatizing prompts (/v1/experimental/generate_prompt, /v1/experimental/improve_prompt, and /v1/experimental/templatize_prompt) are being retired along with the Workbench on August 17, 2026.

  6. Google · Gemini CLI

    Gemini CLI 0.51.0

    2 new6 fixes4 other

    implement Cloud Run webhook ingestion service. egress cloud run service skeleton.

  7. OpenAI · Codex CLI

    Codex CLI 0.144.5

    1 fix

    Improved dangerous-command detection, including more forced rm forms, and provides clearer rejection reasons when commands are denied.

  8. Google · Antigravity

    Codesearch command, copy-on-select, and performance optimizations

    New /codesearch command for regex workspace searches, copy-on-select, async skill discovery, and stability fixes.

  9. Google · Antigravity

    Startup stability fix

    Fixes a bug where an empty or malformed configuration file caused AGY to fail to load on startup.

  10. Mistral AI · Mistral API

    The OCR API confidence_scores_granularity parameter now supports "block" granularity

    "page" returns page-level scores only, "block" returns page-level and block-level scores, and "word" returns page-level and word-level scores.

  11. Mistral AI · New model

    We released OCR 4.1. mistral-ocr-latest and mistral-ocr-4 now point to it

    We released OCR 4.1 (mistral-ocr-4-1). mistral-ocr-latest and mistral-ocr-4 now point to it.

  12. Anthropic · Claude Code

    Claude Code 2.1.211

    1 new24 fixes12 other

    Added --forward-subagent-text flag and CLAUDE_CODE_FORWARD_SUBAGENT_TEXT environment variable to include subagent text and thinking in stream-json output.

  13. Anthropic · Claude API

    Mid-conversation system messages are available on Claude Fable 5, Claude Mythos 5, and Claude Opus 4.8, on…

    No beta header is required. This corrects earlier availability notes.

  14. Anthropic · Claude Code

    Claude Code 2.1.210

    2 new22 fixes9 other

    Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck. Added a startup warning for Write(path), NotebookEdit(path), and Glob(path) permission rules — use Edit(path) or Read(path) instead.

  15. Anthropic · Claude Code

    Claude Code 2.1.209

    1 fix

    Fixed /model and other dialogs being blocked in claude agents background sessions (reverts an overly broad guard).

  16. Anthropic · Claude Code

    Claude Code 2.1.208

    4 new28 fixes13 other

    Added screen reader mode: opt-in plain-text rendering for screen reader users. Run claude --ax-screen-reader, set CLAUDE_AX_SCREEN_READER=1, or add "axScreenReader": true to settings. Added vimInsertModeRemaps setting: map two-key insert-mode sequences like jj to Escape in vim mode.

  17. Anthropic · Claude API

    You can now manage the people in your Claude Enterprise organization with the Admin API, in beta for all…

    Group and custom-role requests require the anthropic-beta: ce-user-management-2026-07-13 beta header; member and invite requests take no beta header. An Admin API key with the read:org_audit scope can also call every user-management GET endpoint.

  18. Anthropic · Claude apps

    HIPAA configuration for your Claude organizations is now self-serve

    You can now manage HIPAA readiness for your Claude organizations yourself. This applies to both Claude Enterprise and the Claude Platform (API). In each product, an eligible admin can review the Business Associate Agreement (BAA), download the implementation guide, and enable the HIPAA configuration in a single flow.

  19. OpenAI · Codex CLI

    Codex CLI 0.144.4

    1 other

    No user-facing changes in this patch release.

  20. Google · Antigravity

    Multi-threaded state handling, subprocess isolation, extra high thinking, and local model MCP

    Release 0.1.7 of the Google Antigravity Python SDK expands end-user control over agent execution environments, strengthens concurrency safety for stateful tools, and introduces deeper reasoning capabilities. Key highlights include atomic multi-threaded state handling for tools and hooks, customizable subprocess environment variable isolation, support for an "extra_high" thinking severity level, and full Model Context Protocol (MCP) and subagent support across local model backends. This release also resolves interactive console prompt clobbering and improves socket discovery under containerized setups.

  21. OpenAI · Codex app

    ChatGPT for iOS

    Added support for inline visualizations in Codex tasks. Improved creating and managing tasks from conversations, with reliable links to newly created tasks. Improved tool activity styling and progress indicators. Improved file-opening feedback. Improved the composer so controls remain visible above the keyboard for long prompts and larger text sizes. Fixed Fast mode selection and restoration for each task. Fixed initial prompts ignoring the selected approval preset. Fixed autocomplete backgrounds and task rows becoming unresponsive during swipe gestures.

  22. OpenAI · Codex CLI

    Codex CLI 0.144.2

    1 fix

    Restored the previous Guardian auto-review policy, request format, and tool behavior after rolling back a prompting regression.

  23. OpenAI · Codex CLI

    Codex CLI 0.144.3

    1 other

    Published a version-only release with no merged pull request changes since rust-v0.144.2.

  24. Google · Antigravity

    Full diff preview, OAuth print mode improvements, and lag fixes

    Added full-screen diffs for file creations, OAuth authorization code pasting in print mode, and 5000+ step latency optimizations.

  25. Google · Antigravity

    Queued messages, plain text files support, and stability improvements

    Added support for queued messages, settings to configure message execution, a send now option, plain text file attachments, and various bug fixes and improvements.

  26. Anthropic · Claude Code

    Claude Code 2.1.207

    17 fixes7 other

    Auto mode is now available without CLAUDE_CODE_ENABLE_AUTO_MODE opt-in on Bedrock, Vertex AI, and Foundry; disable via disableAutoMode in settings. Fixed the terminal freezing and keystrokes lagging while streaming responses containing very long lists, tables, paragraphs, or code blocks.

  27. Anthropic · Claude Code

    Claude Code 2.1.206

    2 new18 fixes7 other

    Added directory path suggestions to /cd, matching /add-dir behavior. Added a /doctor check that proposes trimming checked-in CLAUDE.md files by cutting content Claude could derive from the codebase.

  28. Anthropic · Claude API

    Dreams now supports Claude Fable 5 and Claude Sonnet 5

    We’ve expanded the Access Transparency documentation of cmek_preserve events with a filter example, an example event payload, and two preservation reason codes (policy_violation_investigation, csae_report).

  29. Anthropic · Claude apps

    Updated memory for Claude

    Memory on Claude now works as a set of individual, categorized entries that Claude reads and updates during your conversations, replacing the previous daily memory summary.

  30. Google · Antigravity

    Custom agents flag, in-file keyword search, and Jujutsu diff fixes

    Added --agent flag, in-file keyword search for artifacts, recursive subagent updates, and Jujutsu workspace diff fixes.