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
OpenAI · Codex app
Codex analytics governance docs update
Updated the Codex enterprise governance guide with more detailed coverage of the Analytics dashboard charts, data export options, and enterprise Analytics API endpoints.
Google · Gemini API
Upcoming breaking change: The Interactions API request and response schema and output format configuration…
Upcoming breaking change: The Interactions API request and response schema (outputs → steps) and output format configuration (response_format) are changing. The new schema becomes the default on May 26 and the legacy schema will be removed on June 8.
Google · Gemini CLI
Gemini CLI 0.41.1
1 fixcherry-pick 3627f47 to release/v0.41.0-pr-26542 to patch version v0.41.0 and create version 0.41.1.
Google · Gemini CLI
Gemini CLI 0.41.0
9 new21 fixes14 othersecure.env loading and enforce workspace trust in headless mode. enhance shell command validation and add core tools allowlist.
OpenAI · Codex app
Create Codex access tokens
ChatGPT Enterprise workspace owners and admins can allow permitted members to create Codex access tokens for trusted, non-interactive Codex local workflows. Members can use access tokens to run Codex from scripts, schedulers, and private CI runners with their ChatGPT workspace identity. Learn more in Access tokens.
OpenAI · Codex app
Codex app
Added dictation cleanup plus a configurable dictation dictionary for names, file paths, and code symbols. Added zoom and download controls to the image lightbox. Performance improvements and bug fixes. Improved voice and dictation error messages for microphone, connection, and quota failures. Fixed in-app browser comment markers so they stay aligned across scrolling, zoom, and responsive layout changes. Made pull request creation and recovery flows more reliable by preserving newly created pull request state, classifying more app-server failures as restart-required, and stopping exhausted remote reconnect loops. Additional performance improvements and bug fixes.
Google · Gemini API
Updated File Search to support multimodal search. You can now natively embed and search through images using…
Updated File Search to support multimodal search. You can now natively embed and search through images using the gemini-embedding-2 model. Grounding metadata now includes media_id for visual citations and page_numbers that indicate where information is found. To learn more, see the File Search guide.
Anthropic · Claude Code
Claude Code 2.1.128
25 fixes12 otherBare /color (no args) now picks a random session color. /mcp now shows the tool count for connected servers and flags servers that connected with 0 tools.
Anthropic · Claude API
We’ve launched Workload Identity Federation
Authenticate workloads to the Claude API with short-lived OIDC tokens from your own identity provider (AWS IAM, Google Cloud, GitHub Actions, Kubernetes, Microsoft Entra ID, Okta, SPIFFE, and more) instead of long-lived static API keys. Configure issuers and federation rules in the Claude Console, and the SDK handles token exchange and refresh automatically.
Google · Gemini API
Launched event-driven Webhooks support in the Gemini API to replace polling workflows for the Batch API and…
Launched event-driven Webhooks support in the Gemini API to replace polling workflows for the Batch API and long-running operations.
Anthropic · Claude Code
Claude Code 2.1.126
19 fixes13 otherThe /model picker now lists models from your gateway's /v1/models endpoint when ANTHROPIC_BASE_URL points at an Anthropic-compatible gateway. - Added claude project purge [path] to delete all Claude Code state for a project (transcripts, tasks, file history, config entry) — supports --dry-run, -y/--yes, -i/--interactive, and --all.
xAI · Grok API
Context Compaction
The Context Compaction API is now available. You can shrink long conversations into a shorter context and reuse it in follow-up requests for lower cost, faster time-to-first-token, and sharper responses on long agent loops.
xAI · Grok APIAnnouncement
Custom Voices
You can now clone a voice from a short audio clip and use it across the Text-to-Speech and Speech to Speech APIs. Create and manage your voice catalog from the SpaceXSI console.
xAI · Grok API
Grok Build
Grok Build is now available in beta. Use the interactive TUI, run headlessly in scripts, or build apps and orchestrators with the Agent Client Protocol. Install with a single command: bash customLanguage="bash" curl -fsSL https://x.ai/cli/install.sh | bash For more details, see the Grok Build docs.
xAI · Grok API
Image Search in Web Search
Web Search now supports explicitly searching for images. Enable enable_image_search to let Grok search directly for relevant images; responses can include returned images as Markdown image embeds. For details, see Enable Image Search.
xAI · Grok API
Smart Turn for Streaming STT
The streaming Speech to Text API now supports Smart Turn end-of-turn detection. When enabled via the smart_turn query parameter, an ML model predicts whether the speaker has finished their thought at silence boundaries — reducing false endpointing during dictation, number sequences, and mid-sentence pauses. Use smart_turn_timeout to set a maximum silence fallback.
xAI · Grok API
WebSocket Responses API Mode
WebSocket Responses API mode is now available. Drive the Responses API over a single, long-lived WebSocket connection for lower end-to-end latency on tool-heavy agent workloads.
xAI · New model
Grok Build 0.1
SpaceXSI's coding model, trained specifically for agentic coding workflows. Currently in early access. The model slug is grok-build-0.1.
Google · Gemini CLI
Gemini CLI 0.40.1
1 fixcherry-pick 2194da2 to release/v0.40.0-pr-26153 to patch version v0.40.0 and create version 0.40.1.
Anthropic · Claude API
We’ve retired the 1M token context window beta for Claude Sonnet 4.5 and Claude Sonnet 4
The beta header now has no effect on these models, and requests exceeding the standard 200k-token context window return an error. To use the 1M context window, migrate to Claude Sonnet 4.6 or Claude Opus 4.6, where it’s included at standard pricing with no beta header required.
Google · Gemini API
The gemini-robotics-er-1.5-preview model has been shut down. Use gemini-robotics-er-1.6-preview instead
The gemini-robotics-er-1.5-preview model has been shut down. Use gemini-robotics-er-1.6-preview instead.
Anthropic · Claude Code
Claude Code 2.1.123
1 fixFixed OAuth authentication failing with a 401 retry loop when CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 is set.
Anthropic · Claude API
We’ve released the Claude API skill, an open-source Agent Skill that gives Claude up-to-date reference…
The skill is bundled with Claude Code and available in the Anthropic skills repository.
Anthropic · Claude Code
Claude Code 2.1.122
2 new11 fixes5 otherAdded ANTHROPIC_BEDROCK_SERVICE_TIER environment variable to select a Bedrock service tier (default, flex, or priority), sent as the X-Amzn-Bedrock-Service-Tier header. OpenTelemetry: added claude_code.at_mention log event for @-mention resolution.
Google · Gemini CLI
Gemini CLI 0.40.0
17 new29 fixes32 otherbundle ripgrep binaries into SEA for offline support. add large conversation scenario for performance test.
Anthropic · Claude Code
Claude Code 2.1.121
4 new18 fixes17 otherAdded alwaysLoad option to MCP server config — when true, all tools from that server skip tool-search deferral and are always available. Added claude plugin prune to remove orphaned auto-installed plugin dependencies; plugin uninstall --prune cascades.
Mistral AI · New model
We released Mistral Medium 3.5, our frontier-class multimodal model optimized for agentic and coding use…
Released as open weights under a Modified MIT license.
Google · Gemini CLI
Gemini CLI 0.39.1
Anthropic · Claude API
We’ve released the Rate Limits API, allowing administrators to programmatically query the rate limits…
OpenAI · Codex app
Codex app
Added a tooltip on realtime delegation messages to clarify that Codex uses the surrounding voice conversation as context. Performance improvements and bug fixes. Fixed search in long review files so next and previous results reliably jump to off-screen matches. Kept embedded MCP app panels from restarting or losing state during fullscreen changes and thread reloads. Fixed several desktop regressions, including tray crashes when the local connection is missing, duplicate macOS fullscreen menu entries, and broken global dictation hotkeys on older macOS versions. Additional performance improvements and bug fixes.