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 API

    We’ve added capabilities.thinking.types.between_tools to the Models API

    GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts thinking: {type: "between_tools"}, which turns off up-front thinking. The Compliance API now returns the text each organization member saved as Instructions for Claude in claude.ai and as Global instructions in Cowork, in beta for Claude Enterprise organizations. Fast mode is out of research preview for Claude Opus 5.5, and you no longer need to request access. Fast mode for Claude Opus 5.5 is now available on Claude in Microsoft Foundry for deployments hosted on Azure.

  2. OpenAI · Codex CLI

    Codex CLI 0.163.0

    6 new6 fixes4 other

    Open /config to search preferences across categories, change supported settings immediately, and see which changes require a restart. Send a follow-up while Codex is responding to steer it immediately. Interrupting a turn also stops active Code Mode cells and their nested tool calls.

  3. Anthropic · Claude Code

    Claude Code 2.1.300

    12 new58 fixes18 other

    Added virtualText to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt. Added cache_creation_5m_tokens and cache_creation_1h_tokens to the OpenTelemetry api_request event, splitting cache writes by lifetime.

  4. Anthropic · Claude Code

    Claude Code 2.1.299

    18 new130 fixes42 other

    Added CLAUDE_CODE_DISABLE_FILE_MENTIONS environment variable: Claude gets the paths of @ file mentions to read with its file tools, not the files' contents. Added idle compaction in the terminal: a 200K+ token conversation left idle for about 54 minutes is compacted before its one-hour prompt cache expires, so your next message doesn't reprocess it all.

  5. Anthropic · Claude API

    We’ve launched OpenTelemetry export in beta, so you can trace Messages API requests and Claude Managed…

    The Claude SDK emits spans in Python, TypeScript, C#, Go, Java, PHP, and Ruby. To get spans from the API, add an OpenTelemetry destination in the Claude Console. Claude Managed Agents scheduled deployments are now available on Claude Platform on AWS.

  6. OpenAI · Codex app

    GPT-5.5 retirement in Codex

    Effective October 14, 2026, at noon PDT (19:00 UTC), GPT-5.5 retires from Codex for users signed in with ChatGPT. The OpenAI API and Codex sessions authenticated with an API key aren't affected. Use GPT-6.1 Sol (gpt-6.1-sol) when available to your plan and client. Update workspace defaults, saved model settings, managed configurations, custom agents, scheduled tasks, and scripts that still select gpt-5.5.

  7. Google · Gemini CLI

    Gemini CLI 0.64.0

    14 fixes3 other

    bridge PromptResponse.usage and emit usage_update notifications (#29389). propagate resolved folder trust state in headless mode (#29031).

  8. OpenAI · Codex app

    ChatGPT for iOS

    File citations now open directly in the file viewer. Collapse the entire Projects section to reach recent tasks faster. Faster task and thread loading, with saved task names and recent messages visible while reconnecting. Markdown now renders in sent prompts, with questions quoted above your replies. Queued messages appear immediately, with more reliable handling during turn interruptions. Markdown files open in rendered view by default. Clearer skill names and improved autocomplete after punctuation. Fixed missing Rename prompts and usage percentages on iPad. Plan mode stays selected when returning to the task list. Custom permission mode now respects project-defined permissions. Improved task widget reliability, including when local authentication is enabled for Codex. Usage widgets adapt to accounts with only a weekly limit. Connection errors offer a Retry action without hiding saved messages. Fixed raw image URLs appearing in image-only messages.

  9. Google · Gemini app

    Introducing Gemini 4 Argon: our frontier model for complex tasks, plus 2 more changes

    What: Starting today, Gemini 4 Argon is rolling out globally for Google AI Pro & Ultra subscribers in the Gemini app. 4 Argon is our newest frontier model, built to take your most complex tasks from start to finish. Whether you are analyzing a complex financial report, creating a deck from scattered sources, or building an interactive 3D model, Argon brings frontier intelligence to your everyday workflow, turning your ideas into outputs you can use. Why: We want to make Gemini the most helpful AI assistant for everyone. With the frontier performance of Gemini 4 Argon, you can now turn your most ambitious ideas into real projects.

  10. Google · New model

    New model: Gemini 4 Argon (gemini-4-argon)

    Gemini 4 Argon (gemini-4-argon) generally available (GA): Released Gemini 4 Argon (gemini-4-argon), our most capable model built for complex coding, agentic, math, and science tasks. For API changes, pricing, and migration guidance, see What's new in Gemini 4 Argon.

  11. Anthropic · Claude Code

    Claude Code 2.1.296

    8 new56 fixes15 other

    Added a code key to the Claude apps gateway's managed.policies[]: the same settings as cli, also applied in Claude Desktop's Code tab; beside desktop, it turns on Claude Desktop's gateway mode. Added autoCompactWindow to subagent frontmatter and --agents definitions, so a subagent can auto-compact earlier than the main conversation's window.

  12. Anthropic · Claude API

    You can now let a Claude Managed Agents agent use dynamic workflows, in beta with the…

    For work with many pieces, such as reviewing hundreds of documents, the agent can write a workflow. A workflow is a program that runs many agents in phases and combines their results. The server runs it in the background as a workflow run. To turn dynamic workflows on, set the agent’s multiagent field to {"type": "multiagent_20261001", "workflows": {"type": "enabled"}}. To guide the agent, tell it in its system prompt when to start a run. Follow each run through workflow_run.* events on the session’s event stream.

  13. OpenAI · Codex app

    Composer predictions in Codex

    Composer predictions adds autocomplete-style suggestions for your next message in the Codex desktop app. After Codex responds, it uses the current conversation to suggest a follow-up prompt in the message box. Press Tab to accept the suggestion as an editable draft, or type your own message. Accepting a prediction doesn't send it for you. The feature is available in beta to users aged 18 and older with personal ChatGPT Pro plans in supported regions, in local and SSH threads with GPT-6 Astra and GPT-6.1 Sol. Learn more about composer predictions.

  14. OpenAI · Codex CLI

    Codex CLI 0.162.1

    2 fixes

    Fixed a TUI crash when asynchronous questions contain multiple lines, preserving line breaks and complete hyperlink destinations. Fixed startup failures caused by differences between a running background server's feature settings and CLI defaults. Compatibility checks now apply only to explicit command-line feature overrides.

  15. Anthropic · Claude Code

    Claude Code 2.1.295

    17 new96 fixes30 other

    Added onFailure: "block" for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it through. Added Program Status Protocol (OSC 7501) support: terminals that implement it can show whether Claude Code is working, waiting on you, or done.

  16. Anthropic · Claude Code

    Claude Code 2.1.294

    1 fix1 other

    Fixed prompt and agent hooks written as instructions (such as "Block commands that...") allowing what they should block. Improved how prompt hooks on Stop and SubagentStop written as instructions (such as "Carry on if the build is broken") are judged, so Claude is less likely to stop early.

  17. Anthropic · Claude API

    The Compliance API chat endpoints now also return chats from the unified Claude experience, in beta for…

    The Compliance API can now download Claude Docs documents as Word files, in beta.

  18. OpenAI · Codex app

    Codex app

    Performance improvements and bug fixes. Fixed queued messages getting stuck on Sending and restored Steer in secondary app windows. Improved scrolling and navigation between files in the Changes panel. Added clearer recovery guidance when a tool call needs approval but the chat's permissions prevent approval requests, with a link to those permissions when available.

  19. OpenAI · Codex CLI

    Codex CLI 0.162.0

    6 new6 fixes2 other

    Add tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled. Pin tasks in the agent Command Center with p and keep them in a shared Pinned group when supported by the server.

  20. OpenAI · New model

    GPT-6.1 Sol Ultrafast in Codex and ChatGPT Work

    Ultrafast mode speeds up token generation with GPT-6.1 Sol in Codex and ChatGPT Work. Ultrafast is available on Pro $500 and eligible Enterprise and Edu plans. Enterprise access is off by default; workspace owners must enable it. GPT-6.1 Sol Ultrafast supports inference residency in the United States and Europe (EEA + Switzerland).

  21. Google · Gemini API

    Gemini 3.7 Flash deprecation: gemini-3.7-flash is deprecated and has been replaced by gemini-3.8-flash. It…

    Gemini 3.7 Flash deprecation: gemini-3.7-flash is deprecated and has been replaced by gemini-3.8-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash. Update your model string to gemini-3.8-flash and review the Gemini 3.8 Flash guide. Gemini 3.5 Flash deprecation: gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash. Update your model string to gemini-3.6-flash (or gemini-3.8-flash) and review the Gemini 3.6 Flash guide. Deep Research Agent deep-research-pro-preview-12-2025 deprecation: The deep-research-pro-preview-12-2025 agent is deprecated and will be shut down on October 23, 2026. Migrate your requests to one of the newer Deep Research agent versions: 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. To migrate, update the agent parameter in your interactions.create requests from deep-research-pro-preview-12-2025 to deep-research-preview-04-2026 (or deep-research-max-preview-04-2026).

  22. Anthropic · Claude Code

    Claude Code 2.1.293

    3 new38 fixes15 other

    Added Claude Haiku 5.5 (claude-haiku-5-5), now the default Haiku model on the Anthropic API — 1M context, $0.10/$0.50 per Mtok ($0.50/$2.50 for prompts over 100K). Added agentType to the subagentStatusLine payload, so scripts can tell custom subagent types apart.

  23. Anthropic · Claude API

    We’ve lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million…

    Cache writes and all other prices are unchanged. Code written for Claude Haiku 4.5 can break on Claude Haiku 5.5. The Python and TypeScript SDKs now include classes, in beta, for the browser use tool and the computer use tool. Claude Max and Team plans now include monthly API credits. In Claude Managed Agents, a cloud environment with limited networking now also applies its allowed_hosts to the web_search and web_fetch tools. With limited networking, creating a session fails with a 400 error when an enabled web tool’s allowed_domains has an entry not within allowed_hosts. In Claude Managed Agents, the web_fetch tool now fetches only URLs that have already appeared in the session, for example in the text of a user message, in a web_search result, or in a page that web_fetch returned earlier.

  24. Anthropic · Claude appsAnnouncement

    Claude Haiku 5.5 launch, plus 1 more change

    We just launched Claude Haiku 5.5, the cheapest, fastest, and most capable small model we’ve released, designed for high-volume, cost-sensitive tasks. Max and Team plans now include monthly API credits for running your own apps and agents on the Claude Platform. They roll out over a few days. Claim them by linking a Claude Console organization in Settings > Billing (Max) or Organization settings > Billing (Team). Learn more about monthly API credits for Max and Team plans.

  25. Anthropic · New modelAnnouncement

    New model: Claude Haiku 5.5

    We’ve launched Claude Haiku 5.5 (claude-haiku-5-5), our most capable model tuned for high-volume and latency-sensitive work. It has a 1M token context window, 128k max output tokens, and adaptive thinking with the effort parameter. It’s available on the Claude API, Claude in Amazon Bedrock, Claude Platform on AWS, Claude on Google Cloud, and Claude in Microsoft Foundry.

  26. OpenAI · Codex app

    Codex app

    Performance improvements and bug fixes. Fixed Windows sandbox refresh failures after app updates. Fixed worktree creation and chat forking for WSL repositories whose paths conflicted with Windows directories. Kept the recent chats section collapsed when switching between chats. Fixed Remove from section so it removes a chat from its sidebar section without pinning it.

  27. OpenAI · Codex app

    ChatGPT for iOS

    Page previews now appear inline in responses. Added support for opening Codex task links directly on iOS. Redesigned the approval picker with clearer permission choices. Find plugins from a single Plugins entry in the composer's plus menu. Faster streaming in long threads, with fewer freezes. New tasks keep your selected computer while it reconnects or is offline. Improved worktree support so files and changes match the checkout used on desktop. Fixed task lists remaining empty after connecting. Smoother keyboard transitions when starting tasks and swiping back. Status updates no longer appear as questions that need an answer. Clearer manual pairing code entry, including support for pasting formatted codes.

  28. OpenAI · Codex CLI

    Codex CLI 0.161.0

    6 new6 fixes2 other

    GPT-6.1 Sol is now the default model in the bundled and Amazon Bedrock catalogs. Amazon Bedrock supports multi-agent V2 and Ultra reasoning on compatible models; Bedrock Mantle also accepts AWS GovCloud regions.

  29. Google · Gemini CLI

    Gemini CLI 0.63.0

    11 fixes4 other

    display retry progress indicator during connection recovery (#28340). distinguish missing MCP enablement config from malformed JSON.

  30. Anthropic · Claude Code

    Claude Code 2.1.292

    8 new64 fixes20 other

    Added --marketplace <source> to claude plugin install: adds the marketplace if needed, under the same policy checks as claude plugin marketplace add, then installs the plugin from it. Added an effort parameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask for.