AI release notes

Anthropic · Claude Code·Mar 20, 2026

Claude Code 2.1.81

Added --bare flag for scripted -p calls — skips hooks, LSP, plugin sync, and skill directory walks; requires ANTHROPIC_API_KEY or an apiKeyHelper via --settings (OAuth and keychain auth disabled); auto-memory fully disabled. Added --channels permission relay — channel servers that declare the permission capability can forward tool approval prompts to your phone.

OpenAI · Codex app·Mar 20, 2026

Codex app

Added Floating Composer v2. Added terminal shortcuts for jumping by word and line. Improved plugin discovery surfaces and file-path rendering for saved images. Performance improvements and bug fixes. Fixed sidebar crashes when subagent turn items are missing. Fixed pop-out thread routing and preserved local paths for composer image attachments. Additional performance improvements and bug fixes.

Anthropic · Claude Code·Mar 19, 2026

Claude Code 2.1.80

Added rate_limits field to statusline scripts for displaying Claude.ai rate limit usage (5-hour and 7-day windows with used_percentage and resets_at). Added source: 'settings' plugin marketplace source — declare plugin entries inline in settings.json.

OpenAI · Codex app·Mar 19, 2026

Codex app

Added skills to the @ menu so you can insert them from the composer alongside other mentions. Cmd/Ctrl+F now starts with your current text selection, which makes searching reviews and diffs faster, alongside broader review navigation improvements such as a refreshed file tree and percentage-based file tree resizing. Added a branded loading shimmer while the app starts. Performance improvements and bug fixes. Improved collapsed diff summaries in review. Fixed slash-command focus and composer alignment issues, and polished plugin cards and step details. Additional performance improvements and bug fixes.

Anthropic · Claude Code·Mar 18, 2026

Claude Code 2.1.79

Added --console flag to claude auth login for Anthropic Console (API billing) authentication. Added "Show turn duration" toggle to the /config menu.

Anthropic · Claude API·Mar 18, 2026

We’ve added model capability fields to the Models API

GET /v1/models and GET /v1/models/{model_id} now return max_input_tokens, max_tokens, and a capabilities object. Query the API to discover what each model supports.

OpenAI · Codex app·Mar 18, 2026

Codex app

You can now fork a conversation from an earlier message, not just the latest turn. Added slash commands for switching models and reasoning levels, and made slash commands work in the middle of a draft prompt. Added notifications for plan mode questions so it's easier to notice when Codex needs input. Performance improvements and bug fixes. Fixed thread handoff and subagent navigation issues across worktrees and the VS Code extension. Additional performance improvements and bug fixes.

Google · Gemini API·Mar 18, 2026

Released the new Built-in Tools and Function Calling Combination feature, making it possible to use Gemini's…

Released the new Built-in Tools and Function Calling Combination feature, making it possible to use Gemini's built-in tools alongside custom function calling tools in a single API call. Grounding with Google Maps is now supported for Gemini 3 models going forward.

Anthropic · Claude Code·Mar 17, 2026

Claude Code 2.1.78

Added StopFailure hook event that fires when the turn ends due to an API error (rate limit, auth failure, etc.). Added ${CLAUDE_PLUGIN_DATA} variable for plugin persistent state that survives plugin updates; /plugin uninstall prompts before deleting it.

Google · Gemini CLI·Mar 17, 2026

Gemini CLI 0.34.0

add chat resume footer on session quit. standardize semantic focus colors and enhance history visibility.

Anthropic · Claude Code·Mar 17, 2026

Claude Code 2.1.77

Added allowRead sandbox filesystem setting to re-allow read access within denyRead regions.

Anthropic · Claude apps·Mar 17, 2026

Control Cowork from your phone with a persistent thread (research preview for Pro/Max)

Users on Pro and Max plans can access a persistent agent thread via Claude Desktop or Claude for iOS/Android to manage tasks in Cowork. We're rolling this out to Max plans starting today, and Pro plans over the next two days.

OpenAI · New model·Mar 17, 2026

Introducing GPT-5.4 mini in Codex

GPT-5.4 mini is now available in Codex as a fast, efficient model for lighter coding tasks and subagents. It improves over GPT-5 mini across coding, reasoning, image understanding, and tool use while running more than 2x faster. In Codex, GPT-5.4 mini uses 30% as much of your included limits as GPT-5.4, so comparable tasks can last about 3.3x longer before you hit those limits. GPT-5.4 mini is available in the Codex app, the CLI, the IDE extension, and Codex on the web. GPT-5.4 mini is also available in the API. Use GPT-5.4 mini for codebase exploration, large-file review, processing supporting documents, and other less reasoning-intensive subagent work. For more complex planning, coordination, and final judgment, start with GPT-5.4. To switch to GPT-5.4 mini: In the CLI, start a new thread with: bash codex --model gpt-5.4-mini Or use /model during a session. In the IDE extension, choose GPT-5.4 mini from the model selector in the composer. In the Codex app, choose GPT-5.4 mini from the model selector in the composer. If you don't see GPT-5.4 mini yet, update the CLI, IDE extension, or Codex app to the latest version.

Google · Antigravity·Mar 17, 2026

Fix for customizations creation

Fix for customizations creation.

Google · Gemini CLI·Mar 16, 2026

Gemini CLI 0.33.2

cherry-pick 48130eb to release/v0.33.1-pr-22665 [CONFLICTS].

Anthropic · Claude API·Mar 16, 2026

We’ve launched the display field for extended thinking, letting you omit thinking content from responses for…

Set thinking.display: "omitted" to receive thinking blocks with an empty thinking field and the signature preserved for multi-turn continuity. Billing is unchanged. Learn more in Controlling thinking display.

OpenAI · Codex app·Mar 16, 2026

Codex app

Added back and forward buttons in the header so you can move between recent screens more quickly. Added an Open in Finder, Open in Explorer, or Open in File Manager action from thread menus to jump straight to a thread's project folder. Performance improvements and bug fixes. Improved resume and thread error toasts with clearer details when something goes wrong. Additional performance improvements and bug fixes.

Google · Gemini API·Mar 16, 2026

Introduced revamped Usage Tiers and Billing Account spend caps for a better user billing experience

Introduced revamped Usage Tiers and Billing Account spend caps for a better user billing experience.

Mistral AI · New model·Mar 16, 2026

We released Mistral Small 4, a hybrid model unifying instruct, reasoning, and coding in a single multimodal…

We released Leanstral (labs-leanstral-2603), our first open-source code agent designed for Lean 4 formal proof engineering.

Anthropic · Claude Code·Mar 14, 2026

Claude Code 2.1.76

Added MCP elicitation support — MCP servers can now request structured input mid-task via an interactive dialog (form fields or browser URL). Added new Elicitation and ElicitationResult hooks to intercept and override responses before they're sent back.

Anthropic · Claude Code·Mar 13, 2026

Claude Code 2.1.75

Anthropic · Claude API·Mar 13, 2026

The 1M token context window is out of beta for Claude Opus 4.6 and Sonnet 4.6, at standard pricing

Requests over 200k tokens work automatically for these models with no beta header required. The 1M token context window remains in beta for Claude Sonnet 4.5 and Sonnet 4. We’ve removed the dedicated 1M rate limits for all supported models. We’ve raised the media limit from 100 to 600 images or PDF pages for each request when using the 1M token context window.

Google · Gemini CLI·Mar 12, 2026

Gemini CLI 0.33.1

cherry-pick 8432bce to release/v0.33.0-pr-22069 to patch version v0.33.0 and create version 0.33.1.

Anthropic · Claude Code·Mar 12, 2026

Claude Code 2.1.74

Added actionable suggestions to /context command — identifies context-heavy tools, memory bloat, and capacity warnings with specific optimization tips. Added autoMemoryDirectory setting to configure a custom directory for auto-memory storage.

Anthropic · Claude apps·Mar 12, 2026

Claude creates interactive charts, diagrams and visualizations

Claude can now create custom charts, diagrams and other visualizations in-line in its responses.

OpenAI · Codex app·Mar 12, 2026

Codex app

Change the Codex app appearance in Settings by choosing a base theme, adjusting accent, background, and foreground colors, and changing the UI and code fonts. You can also share your custom theme with friends. !Codex app theme settings showing custom themes, color controls, and font settings. You can now choose whether automations run locally or on a worktree, define custom reasoning levels and models, and use templates to find inspiration for new automations. !Automations settings showing local and worktree options alongside scheduling controls. Performance improvements and bug fixes. Various bug fixes and performance improvements.

Google · Gemini API·Mar 12, 2026

Introduced project-level spend caps to billing in AI Studio

Introduced project-level spend caps to billing in AI Studio.

Mistral AI · Mistral API·Mar 12, 2026

We added Custom Guardrails support for Agents and Conversations

Guardrails can now be configured directly on an Agent via the guardrails parameter. Guardrails can be passed per-request on POST /v1/conversations using the guardrails field. Guardrails can be passed per-request on POST /v1/chat/completions using the guardrails field.

Mistral AI · New model·Mar 12, 2026

We released Mistral Moderation 2603

We released Mistral Moderation 2603 (mistral-moderation-2603).

Anthropic · Claude Code·Mar 11, 2026

Claude Code 2.1.73

Added modelOverrides setting to map model picker entries to custom provider model IDs (e.g. Bedrock inference profile ARNs). Added actionable guidance when OAuth login or connectivity checks fail due to SSL certificate errors (corporate proxies, NODE_EXTRA_CA_CERTS).