This week in AI dev tools

Generated by Speakeasy CLI 2026-11-01 13:00:38 Generated SDK baseline differences The published SDK or generator baseline differs from the baseline used by the OpenAPI changelog.…

Fixed With --screen-reader, failed and rejected tool calls, errors such as an unknown command, and warnings now begin with "Error:" or "Warning:" instead of reading like any…

Full Changelog : v0.67.0-nightly.20261031.g6814e00d6...v0.67.0-nightly.20261101.g6814e00d6

Fixed apply_patch keeps the line ending of every line it does not change in a file that mixes LF and CRLF endings, instead of rewriting the whole file to the ending of its first…

What's Changed fix(core): honor .git/info/exclude and core.excludesFile in shadow repo by @urielefrenvirtusa in #30034 fix(core): flush pending SSE event buffer at stream EOF in…

What's changed Added CLAUDE_CODE_DISABLE_ULTRATHINK , which turns the ultrathink keyword off Added pooled group budgets to the Claude apps gateway: one monthly budget that a…

What's changed Added permissions.blockReadsExemptPaths to the Settings type: paths, read only from --settings and settings the host sends, that…

Highlights Worktree and Shell Mode Shortcuts : Press ⌘⌥O on macOS or Ctrl+Alt+O on Windows and Linux to choose a worktree, and ⌘⌥B or Ctrl+Alt+B to choose its base branch. ⌘⇧X or…

Highlights Persistent Desktop Terminals : Desktop terminals now belong to the session, survive server restarts with their scrollback, and stay synchronized with the TUI and other…

Highlights Use Claude Code in OpenCode : Install Claude Code, run claude auth login , then select Claude Agent in /connect to use your Claude Code login and models. ( #58782 )…

Changes since 1.2.18 release(langgraph): 1.2.19 ( #9504 ) release(checkpoint-sqlite): 3.1.3 ( #9505 ) fix(langgraph): keep trace_policy from rewriting streamed node payloads (…

Changes since checkpointsqlite==3.1.2 release(checkpoint-sqlite): 3.1.3 ( #9505 ) release(checkpoint): 4.3.1 ( #9447 ) fix(checkpoint): reject NUL bytes in namespace labels (…

Changes since sdk==0.4.10 release(langgraph): 1.2.19 ( #9504 ) release(sdk-py): 0.4.11 ( #9503 ) test(sdk-py): check that a reconnect loop resumes after the newest event ( #9483…

Patch Changes 89b76ce : Centralize xAI language, image, speech, transcription, and realtime capabilities in a shared model catalog, preserving request policies and generating…

Patch Changes @ai-sdk/harness@1.0.170

Patch Changes ai@7.0.159

Patch Changes ai@7.0.159

Patch Changes Updated dependencies [ a1a772f ] @ai-sdk/provider-utils@3.0.43 @ai-sdk/openai-compatible@1.0.60

Patch Changes Updated dependencies [ a1a772f ] @ai-sdk/provider-utils@3.0.43 @ai-sdk/openai-compatible@1.0.60

Render UX verification reports with existing Desktop artifact access …

Changes Bumped sentence-transformers to 5.6.0 , addressing CVE-2026-68770 (vulnerable range 5.6.0) ( #6932 ) Bumped pyjwt to 2.15.1 and mocked PyJWKClient.fetch_data in JWKS auth…

Added /release-notes (alias /whatsnew ) browses the release notes of every Vibe version in a searchable, full-screen view. Provider option preserve_api_base = true keeps a custom…

OpenAI will honor a shared robots.txt signal to help website operators communicate their AI training preferences to participating providers.

OpenAI is strengthening violence prevention in ChatGPT with expanded safeguards, earlier interventions, and a new commitment to public safety reporting.

OpenAI shares excerpts from court briefs by creators, academics, accessibility advocates, and legal experts, among others, on how fair use supports AI training and innovation.

What's Changed docs(readme): clarify Gemini CLI scope, limitations, and tool landscape by @LyalinDotCom in #29995 fix(cli): bound inline history re-render after terminal width…

What's changed Added permissions.blockWritesOutsideWorkingDirectories : Write, Edit and NotebookEdit refuse paths outside the working directories in every permission mode Added…

What's changed Added sandbox_required_unavailable to startup_failure_reason , for the result Claude Code writes when a required sandbox cannot run Added…

opencode-pty 0.4.0 (protocol 7) from packages/process-daemon, published to npm as @opencode/pty@0.4.0.

Highlights Image Generation by Default : When a connected provider supports image models, agents can now use experimental_image_generate without additional configuration. Set its…

opencode-pty 0.3.3 (protocol 7) from packages/process-daemon, published to npm as @opencode/pty@0.3.3.

Highlights Keep Working Toward a Goal : Run /goal objective in the TUI or Desktop to let the session continue until a reviewer confirms the objective is met. Use /goal pause ,…

Changes since langchain-core==1.7.2 release(core): 1.7.3 ( #41564 )

Changes since langchain-core==1.7.1 release(core): 1.7.2 ( #41562 ) feat(core): add add_notification_metadata and get_notification_metadata ( #41540 ) fix(core): stop…

New Features Added keyboard-driven transcript selection with word, line, and page motions, integrated search, and configurable shortcuts. ( #57221 , #57222 , #57223 , #57224 )…

Patch Changes ai@6.0.319

Patch Changes Updated dependencies [ 61a315e ] @ai-sdk/provider-utils@5.0.71 @ai-sdk/openai-compatible@3.0.81

Patch Changes 61a315e : fix: map the top-level reasoning option consistently across providers Providers now resolve reasoning the same way: A provider-specific reasoning setting…

Patch Changes Updated dependencies [ 033f8d9 ] Updated dependencies [ e7a8988 ] Updated dependencies [ 2c12e25 ] Updated dependencies [ 6eab0f7 ] @ai-sdk/harness@1.0.168

Patch Changes 0cc4921 : graduate LanguageModelStreamPart to stable and deprecate Experimental_LanguageModelStreamPart 077cfb3: feat(ai): Graduate filterActiveTools from…

Patch Changes Updated dependencies [ 0cc4921 ] Updated dependencies [ 61a315e ] Updated dependencies [077cfb3] Updated dependencies [ eb768e2 ] ai@7.0.157…

OpenAI’s updated Model Spec outlines five core values to guide more capable AI toward sound judgment, human agency, and faithfulness to human intent.

OpenAI uses layered monitoring to detect frontier model misalignment and unauthorized agent behavior so responders can intervene before incidents escalate.

Ropes & Gray is developing AI for transactional diligence with OpenAI. Lawyers review grouped documents, summaries, and reports before advising clients.

Credit Saison’s ChatGPT Enterprise pilot delivered 954% ROI. See how leaders and employees helped turn the results into companywide adoption.

Generate, edit, and preview PDFs or Docs directly in Gemini. Use the new full-screen editor to refine your files today. See what's new in Gemini.

Turn raw notes into high-impact, ATS-friendly resume bullets using Gemini. Follow these four steps to polish your professional profile. Get the details.

🪣 Copy files into Buckets with HfFileSystem HfFileSystem raised NotImplementedError on any copy involving a Bucket. Copying into a Bucket now works from the same Bucket, from…

v2.4.0.rc0 pre-release

New Models Mistral Large 4 (Le Chonk) Mistral Large 4 is Mistral's largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model…

The weights of Mistral Large 4 (Le Chonk) are now open. A 1T parameter multimodal model, and best open-weight model for coding, trained in Europe.

LFM3 on Linux and Windows Liquid AI's LFM3 models, including text-to-speech in lfm3-audio and lfm3-omni , now run on Linux and Windows as well as Apple silicon. Full Changelog :…

This temporary patch works around a regression on older versions of MacOS ggml_metal_library_compile_all: failed to build 'unary' library

llama.cpp: version bump b11963 ( #19360 )

✨ Features Allowlist: require HTTPS and validate redirects, block on policy failure #12619 Allow callers to supply Goose session IDs #13098 🐛 Bug Fixes Linux window icons…

https://code.visualstudio.com/updates/v1_144

Today, we are rolling out immersive explorations in the new Gemini student hub.

Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.

XREAL AURA, the first wired XR glasses powered by Android XR, lets you work, watch, and play anywhere with Gemini by your side.

We’re announcing new connected apps partners and a new platform for developers to build and track their apps in one place.

opencode-pty 0.3.2 (protocol 7) from packages/process-daemon, published to npm as @opencode/pty@0.3.2.

Core Bugfixes Failed TUI worker requests now return an error instead of leaving the caller hanging. ( @Nowaker ) Thank you to 1 community contributor: @Nowaker : fix(opencode):…

GitHub Copilot Fusion is generally available. Instead of picking a model for each task, choose Copilot Fusion and let Copilot intelligently route and orchestrate which models it…

Work doesn't always fit in a single repository or session. A feature can span several repositories. A launch plan can pull in specs, designs, and assets without touching a…

Enterprises working with a GitHub or Microsoft account team can now get Copilot included with GitHub Enterprise for every licensed user. Previously, you had to manage two things:…

You can now work through your repository's GitHub code scanning alerts without leaving the GitHub Copilot app. The new GitHub security extension, now in public preview, lets you…

Agents should understand more than your codebase they should understand how your team works. Your preferences, repository conventions, skills, and custom instructions guide how…

Shared Copilot Automations are rolling out, enabling teams to build and maintain AI-powered workflows together. With Copilot Automations, you can combine prompts, triggers, and…

This week's release includes syntax highlighting for Go 1.27 generic methods, an option to open README files by default, and AI commit messages that follow your repository's…

This week's release includes Pyrefly as an optional built-in Python language server, the ability to expand and inspect nested variable values directly in debugger hovers, and…

Changes since langchain-core==1.7.0 release(core): version 1.7.1 ( #41548 ) fix(core): preserve gateway tracing metadata in v3 streams ( #41504 ) fix(core): escape node metadata…

OpenAI and ServiceNow expand their partnership to bring OpenAI models and agents into ServiceNow and ServiceNow workflows into ChatGPT and Codex.

How AI might enter the org chart—beneath, beside, and between us.

See how Legora uses OpenAI models, ChatGPT, and Codex to accelerate legal workflows, expand contract analysis, and free lawyers to focus on higher-value work.

See how Legora uses OpenAI models, ChatGPT, and Codex to accelerate legal workflows, expand contract analysis, and free lawyers to focus on higher-value work.

What's Changed fix(core): allow trusted system paths on Android (Termux) for ripgrep resolution ( #21836 ) by @amelidev in #29884 fix(core): normalize CRLF line endings before…

2026-10-27 Selecting Copilot Fusion High or Max in /model now works from long-context sessions

Changes since langchain-anthropic==1.7.6 release(anthropic): 1.7.7 ( #41538 ) fix(anthropic): trace resolved reasoning effort ( #41536 ) chore(infra): relax third-party…

Patch Changes 7b79338 : expose costInUsdTicks in responses provider metadata

Patch Changes Updated dependencies [ 57086ff ] Updated dependencies [ 95348b3 ] @ai-sdk/provider-utils@5.0.70 @ai-sdk/openai-compatible@3.0.80

Patch Changes 0eb8de6 : fix(xai): stop emitting each citation twice when streaming responses with web or X search Updated dependencies [ 57086ff ] Updated dependencies [ 95348b3…

Patch Changes @ai-sdk/harness@1.0.166

Patch Changes Updated dependencies [ 57086ff ] Updated dependencies [ b6b9dca ] Updated dependencies [ 95348b3 ] @ai-sdk/provider-utils@5.0.70 ai@7.0.155

Patch Changes Updated dependencies [ 57086ff ] Updated dependencies [ b6b9dca ] Updated dependencies [ 95348b3 ] @ai-sdk/provider-utils@5.0.70 ai@7.0.155

Fixes and changes

Fixed Selecting Copilot Fusion High or Max in /model now works from long-context sessions

2026-10-27 Managed model "fusion" now starts sessions on Auto and applies fusionTier settings Interactive and SDK Autopilot sessions keep waiting for attached background tasks…

Liquid AI LFM3 LFM3 is Liquid AI's new family of small models built for local agents, tool calling, and structured output, on Liquid's new tri-hybrid architecture. The family…

mlx: add LFM3 and d1 models ( #19333 )

What's Changed mlx: preserve small-image detail for compact Gemma 4 vision towers by @dhiltgen in #19247 MLX, MLX-C: version bump - prompt speed up for gemma/flint/laguna by…

GitHub Copilot now supports server-to-server authentication for GitHub Apps installed on organizations, available in public preview. Services and agents built with the GitHub…

What's Changed Update ROADMAP.md to no longer reference outdated 2025 roadmap by @DavidAPierce in #29723 Changelog for v0.65.0-preview.0 by @gemini-cli-robot in #29739…

What's Changed Changelog for v0.65.0 by @gemini-cli-robot in #29853 chore(release): bump version to 0.67.0-nightly.20261020.gb041de017 by @gemini-cli-robot in #29854 Changelog…

What's Changed fix(core): classify project spending cap errors as terminal quota errors by @jesussamuel-byte in #29961 fix(acp): include MCP server and tool metadata in…

What's changed Added oidc.user_id_claim to the Claude apps gateway, to identify people by an id_token claim other than sub , such as Microsoft Entra ID's oid Added click to send:…

What's changed Added autoMode , skipAutoPermissionPrompt , useAutoModeDuringPlan and permissions.disableAutoMode to the Settings type Added unanswered ( skipped , replied_in_chat…

New Features Added a built-in Google Cloud Vertex AI provider, configured with model_provider = "gcp" . ( #56265 ) Added GPT-6.1 Terra to the model catalogs. ( #57337 ) Added a…

GPT-6 Astra tops Retell’s voice agent benchmark, while Codex helps it reach a $1.6M annual revenue run rate per employee.

OpenAI and Oracle are expanding their partnership to bring business applications and AI agents into ChatGPT and power new Oracle offerings.

With OpenAI Daybreak, Check Point speeds up the research behind new security protections, enabling its analysts to turn vulnerability intelligence into customer defenses faster.

From deep research to interactive design, here are eight examples of what Gemini 4 Argon, our most intelligent model yet, is capable of.

You can now set content guidelines on text API requests. Add a guidelines array to a Chat Completions or Responses API request to set how Grok handles content in the nsfw ,…

Highlights Create, install and share Desktop plugins (experimental) ( #55246 , #59469 , #59489 ) Refreshed the desktop app experience ( #56898 , #58865 , #55838 , #57962 ) Add…

Changes since langchain-openai==1.7.2 test(openai): use current lightweight model in integration tests ( #41509 ) release(openai): 1.7.3 ( #41506 ) chore(model-profiles): refresh…

Fixes and changes

Assisted permissions are now generally available in GitHub Copilot CLI, GitHub Copilot app, and Visual Studio Code. When Copilot requests permission to run a command, access a…

GPT-6.1 Terra, OpenAI's newest model, is now generally available in GitHub Copilot. It is designed for everyday agentic coding and terminal work at a lower cost than GPT-6.1 Sol.…

Added Skills added or edited on disk are picked up by running sessions without /reload The footer shows the active model and its thinking level next to the token counter, and…

How Greptile uses GPT-6 Astra to test user workflows, Daybreak to strengthen security, and Codex to reduce rework.

OpenAI shares model results on the Kakeya conjecture, Exponential Time Hypothesis, and quantum chromodynamics—and how researchers can verify and build on them.

CodeRabbit uses GPT-6.1 Sol to investigate security risks across complex codebases. Its security agent helps developers review findings and proposed fixes.

Explore OpenAI Signals data on 165 work activities across nearly 100 countries, revealing how people use ChatGPT for work and how usage changes over time.

Fanatics uses OpenAI to help fans complete their game-day outfits with Shop the Look. Testing across roughly 30,000 MLB products showed 10% higher engagement.

See how OpenAI engineers use Codex Ultrafast to investigate incidents in minutes. Explore faster security analysis, code refactoring, and daily workflows.

What's changed Added cacheCreationEphemeral5mInputTokens and cacheCreationEphemeral1hInputTokens to ModelUsage , splitting cacheCreationInputTokens by cache lifetime Changed…

What's changed Added --hold-idle-file and --max-hold-min to self-hosted-runner , to keep an idle session while your host reports processes it left running Added a tip for the…

Changes since 1.2.17 release(checkpoint): 4.3.1 ( #9447 ) release(langgraph): 1.2.18 ( #9445 ) fix(langgraph): let error_handler recover on every path and stream failed task…

Changes since sdk==0.4.9 release(checkpoint): 4.3.1 ( #9447 ) release(langgraph): 1.2.18 ( #9445 ) release(sdk-py): 0.4.10 ( #9446 ) fix(sdk-py): retry runs.wait with a bodyless…

Changes since checkpoint==4.3.0 release(checkpoint): 4.3.1 ( #9447 ) fix(checkpoint): reject NUL bytes in namespace labels ( #9383 ) chore(deps): bump certifi from 2026.1.4 to…

Changes since cli==0.4.39 release(cli): 0.4.40 ( #9443 ) feat(cli): send the upload headers the control plane returns ( #9396 )

Changes since cli==0.4.38 release(cli): 0.4.39 ( #9442 ) feat(cli): add --json to deploy list ( #9395 ) chore(deps): bump zod from 4.3.6 to 4.6.7 in /libs/cli/js-examples ( #9432…

Patch Changes Updated dependencies [ e64ed82 ] Updated dependencies [ 27a53b4 ] @ai-sdk/provider-utils@5.0.69 @ai-sdk/openai-compatible@3.0.79

Patch Changes Updated dependencies [ e64ed82 ] @ai-sdk/provider-utils@5.0.69

Patch Changes @ai-sdk/harness@1.0.165

Patch Changes Updated dependencies [ 47236dd ] Updated dependencies [ c8e8866 ] Updated dependencies [ e64ed82 ] Updated dependencies [ 1cf95c6 ] ai@7.0.154…

Patch Changes Updated dependencies [ 47236dd ] Updated dependencies [ c8e8866 ] Updated dependencies [ e64ed82 ] Updated dependencies [ 1cf95c6 ] ai@7.0.154…

Patch Changes Updated dependencies [ e64ed82 ] @ai-sdk/provider-utils@5.0.69

Release v5.21.0 New Model additions MiniCPM-OCR MiniCPM-OCR is a document-understanding model from OpenBMB's MiniCPM-V family. It keeps the MiniCPM-V 4.6 architecture, which…

We asked 15 college students about their favorite Gemini features for learning, studying, taking notes, and more.

Objective Fixes #62562 tree-sitter-go is not being actively maintained. There have been 2 new versions of Go released since the most recent commit to main, the most recent (Go…

Closes #57664 Updates crash-context transitive dependency (ergo the patch section) to include rust-minidump/minidump-writer#249 fix: given the latest release was a few months…

New projects using the Generate Content API ( generateContent , streamGenerateContent , and batchGenerateContent ) on the paid tier now store requests by default ( store=true ),…

Added Cloud tasks: Settings API Configuration has a Local | Cloud toggle when cloud sessions are on. Cloud picks the Cline model new cloud tasks run on, saved separately from…

A new Changes button in the session header shows the session's line counts and opens a pane listing the files changed in the last turn or across the whole session, with a diff of…

Opening a task that's already running in another Cline app now attaches to that run instead of starting a second one that couldn't be stopped. If an app closes mid-task, requests…

Starting a session that already has a run in progress now reattaches to the live session instead of replacing its runtime. Before, the original run kept going but couldn't be…

@cline/ui@0.2.0

@cline/core@0.2.0