Every AI dev-tool release, in one place.

What's Changed llama: update llama.cpp to b11521 for decision models and EmbeddingGemma 2 by @jmorganca in #18917 server: reuse verified manifests and loaded models in inference…

Add Kev decision scoring to MLX Load Kev models with their FP32 decision head and release metadata. Support System One scoring with shared-state caching and Kev-specific limits.…

Merged PR 779: Fix MCP sandbox permission approval isolation (MSRC 13… …8669) ## Summary - Restrict root sandbox configuration to shared deny rules; ignore legacy root…

Fixes and changes

2026-10-13 Add agent-scoped declarative hooks for custom agents Remote plugin marketplace and plugin fetches retry once with your signed-in GitHub token after HTTPS auth fails.…

Fixed Remote plugin marketplace and plugin fetches retry once with your signed-in GitHub token after HTTPS auth fails. Streamed responses behind TLS-intercepting proxies complete…

Changes since cli==0.4.33 release(cli): 0.4.34 ( #9300 ) feat(cli): add --json to deploy listeners list ( #9243 )

What's Changed refactor(a2a-server): implement V1 to V2 settings migration logic by @jvargassanchez-dot in #29450 fix(acp): bridge PromptResponse.usage and emit usage_update…

What's Changed fix(cli): enforce read-only workspace settings in untrusted folders by @jvargassanchez-dot in #29583 fix(core): avoid duplicate tool response turns when resuming…

What's Changed fix(cli): keep loading other extensions when one fails the allowlist check by @jesussamuel-byte in #29720 Full Changelog :…

Gemini 4 Argon, Google's newest frontier model, is now generally available in GitHub Copilot. It is designed for complex coding, agentic, and reasoning tasks. In early testing,…

Enterprise administrators can now require supported GitHub Copilot clients to retrieve current server-managed settings at startup instead of relying on a cached policy. We are…

Learn more about our approach to safety and security for Gemini 4 Argon.

Gemini 4 Argon brings frontier reasoning and agentic coding to the Google Gemini app. Google AI Pro and Ultra subscribers can now access Gemini 4 Argon.

Build complex software and cybersecurity workflows with Google Gemini 4 Argon. Check out the Gemini API Developer Guide and read the Google Antigravity and Android Studi…

Co-authored-by: github-actions[bot] 41898282+github-actions[bot]@users.noreply.github.com

Patch Changes Updated dependencies [ 6617f11 ] Updated dependencies [ aae69cb ] Updated dependencies [ a7a66f5 ] Updated dependencies [ 52e3f53 ] Updated dependencies [ 6c0295c ]…

Patch Changes 6d6900f : fix(workflow): pass URL-backed inputs through workflow functions before model steps URL-backed image and file inputs are no longer downloaded in the…

Patch Changes ai@7.0.139

Summary Adds Sonnet 5.5 and Haiku 5.5. Reasoning can't be disabled for Sonnet 5.5, but it added a new reasoning level that we can use instead. Self-review I've reviewed my diff…

Follow-up to #65158 Release Notes: N/A (Nightly only)

A new outline along the left edge of the conversation lists each prompt you sent. Hover a mark to preview the prompt, and click it to jump there Plugins that fail to load or…

Changed With no model chosen, the Cline and OpenRouter providers now use Claude Sonnet 5.5. For Cline, that's the first model in Cline's recommended list. Selecting ai shows its…

Plugins now load inside the hub instead of a separate node or bun process, so the CLI no longer needs a JavaScript runtime on your PATH to run plugins. A plugin that fails to…

Higgsfield brings creators longer videos with GPT-6 Astra, precise visuals with GPT-Image-2.5, and a path to voice filmmaking with GPT-Live.

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…

release: v2.0.28

Origin integrates with over 20 apps for deployments, CI, code review, security, monitoring, and project management, and the marketplace is now open to public submissions.

Changes since checkpointpostgres==3.1.2 release(checkpoint-postgres): 3.1.3 ( #9287 ) fix(checkpoint-postgres,checkpoint-sqlite): treat an empty checkpoint_id as the latest in…

Changes since checkpointsqlite==3.1.1 release(checkpoint-sqlite): 3.1.2 ( #9288 ) fix(checkpoint-postgres,checkpoint-sqlite): treat an empty checkpoint_id as the latest in delta…

Changes since sdk==0.4.6 release(sdk-py): 0.4.7 ( #9289 ) release(langgraph): 1.2.15 ( #9283 ) fix(sdk-py): end a thread stream's run only on a root lifecycle event ( #9228 )…

Fixes and changes

Added Add agent-scoped declarative hooks for custom agents Improved Inline images render by default on supported terminals without enabling experimental mode. Use /settings…

2026-10-12 Interactive sandbox settings suggest possible environment secrets and let you add masking hosts before saving. Make model IDs in /model and /config model…

Enterprise administrators can now use telemetry in managed settings to attribute GitHub Copilot activity to a user without collecting their prompts, responses, or tool content.…

Fixed an issue where no fonts would show for the markdown preview configurations in the settings UI. ( #65446 ) Fixed crashes on tab-indented code blocks ( #65406 ) Fixed edit…

Fixed an issue where no fonts would show for the markdown preview configurations in the settings UI. ( #65447 ) Fixed edit predictions retaining single worktree files ( #65400 )…

Changes since langchain==1.4.4 release(langchain): 1.4.5 ( #41226 ) feat(langchain): accept summarizer in SummarizationMiddleware ( #41225 )

Changes since langchain-anthropic==1.7.5 release(anthropic): 1.7.6 ( #41221 ) chore(model-profiles): refresh model profile data ( #41145 ) feat(core,anthropic,openai): declare…

Changes since langchain-openai==1.7.0 release(openai): 1.7.1 ( #41222 ) feat(core,anthropic,openai): declare mid-conversation support in model profiles ( #41180 )

Co-authored-by: uyencss uyencss@users.noreply.github.com Co-authored-by: Aiden Cline aidenpcline@gmail.com

release: v2.0.27

MLX, MLX-C: version bump ( #18956 )

Full Changelog : v0.65.0-nightly.20261010.g9b6e0265d...v0.65.0-nightly.20261012.g9b6e0265d

What's Changed ollama launch claude no longer shows a warning about Claude connectors by @hoyyeva in #18878 ollama launch codex no longer warns about service tiers by @hoyyeva in…

Core Improvements Run opencode upgrade --major to upgrade to OpenCode 2. Bugfixes Allow the OpenAI ultrafast service tier. Validate PTY connection origins and tickets before…

This update brings more control over default models and MCP server in GitHub Copilot for JetBrains. It also makes diagnostics easier to address, improves chat navigation and…

Takes the v2 tree, with packages/console, packages/web, packages/stats, packages/function, infra and sst.config.ts merged up to latest dev, and retargets V2 publishing and…

Fixed Make model IDs in /model and /config model case-insensitive and save canonical IDs

Added Interactive sandbox settings suggest possible environment secrets and let you add masking hosts before saving. Fixed Keep /allow-all available during startup while…

What's Changed fix(cli): handle JSON parse and response stream errors in fetchJson by @jesussamuel-byte in #29658 fix(core): preserve line terminators in truncateString by…

This week's updates make Copilot easier to use across accounts and environments, with more control over what agents can access and how you manage their work. GitHub Copilot…

What's Changed fix(patch): cherry-pick 2ce1a69 to release/v0.64.0-preview.0-pr-29672 to patch version v0.64.0-preview.0 and create version 0.64.0-preview.1 by @gemini-cli-robot…

Bug Fixes Fixed a TUI crash when asynchronous questions contain multiple lines, preserving line breaks and complete hyperlink destinations. ( #51866 ) Fixed startup failures…

What's changed 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…

What's changed Added claude_code_version to the initialize control response so clients know the CLI version before the first turn Added autoCompactWindow to AgentDefinition , so…

Improved Interactive sessions in git repositories reach the input prompt sooner Timeline now shows whether you, Assisted Permissions, policy, or unattended fallback made each…

Co-authored-by: v0 it+v0agent@vercel.com

What's Changed Add Design Mode browser bridge and payload helpers by @alex-grover in #253 Release v3.0.10 by @github-actions[bot] in #254 Fix release lockfile drift with a second…

Add Design Mode browser bridge and payload helpers Wire Design Mode into the v0-clone example Stream Design Mode progress and compact user message rendering Use shared Acme Team…

server: skip local model compatibility migration ( #18908 )

Model upgrades Models downloaded with earlier versions of Ollama are upgraded in the background the first time you run them, for better performance and compatibility when running…

Features api: add types for the Chat and Cowork unified analytics metrics api: add workflows, multiagent configuration and thread status filtering to Managed Agents Chores…

Features api: add types for the Chat and Cowork unified analytics metrics api: add workflows, multiagent configuration and thread status filtering to Managed Agents Chores…

Added The app-server reports which process holds a stored session, and pushes a change when that process lets go of it, so a client can show a session open elsewhere as read-only…

Generated by Speakeasy CLI 2026-10-09 08:29:55 Generated SDK baseline differences The published SDK or generator baseline differs from the baseline used by the OpenAPI changelog.…

Discover how Sophos uses OpenAI’s Daybreak to cut cyber-threat investigation time by 96% and automate 52% of MDR cases while preserving human oversight.

Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.

Minor release off the new release-1.5.x branch. 108 commits since v1.4.0 . Breaking changes Serve conversations and prompts with responses, or when explicitly listed ( #6561 ) An…

Minor Changes edfa410 : fix: Use current Vercel authentication configuration for restored sessions and disable legacy authentication fallback when current authentication is…

Patch Changes Updated dependencies [ 40f7de2 ] Updated dependencies [ 836cb50 ] Updated dependencies [ 05241c7 ] Updated dependencies [ 4137680 ] Updated dependencies [ 8ee5055 ]…

Patch Changes df20529 : fix: Preserve audio interruption after generation with transport-appropriate buffer clearing and response-specific playback duration. Updated dependencies…

Changes since langchain==1.4.3 release(langchain): 1.4.4 ( #41163 ) fix(langchain): (SummarizationMiddleware) retry summary step on context overflow ( #41159 ) chore(deps): bump…

Changes since langchain-core==1.6.8 release(core): 1.6.9 ( #41160 ) feat(core): accept a callable in with_retry ( #41158 )

Changes since langchain-openai==1.6.7 release(openai): 1.7.0 ( #41154 ) feat(openai): support decisions api ( #41125 ) chore(deps): bump langgraph-sdk from 0.4.4 to 0.4.6 in…

New Features Add tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled. ( #50148 ) Pin tasks in the agent Command…

What's Changed chore: update SDK from production OpenAPI by @github-actions[bot] in #248 chore: update SDK from production OpenAPI by @github-actions[bot] in #251 chore: update…

What's changed Added overageEnabled to SDKRateLimitInfo : on usage-limit warnings, whether the account has extra usage turned on Fixed an MCP server added with mcp_set_servers…

What's changed Updated to parity with Claude Code v2.1.294 Update npm install @anthropic-ai/claude-agent-sdk@0.3.294 # or yarn add @anthropic-ai/claude-agent-sdk@0.3.294 # or…

What's changed 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…

What's changed 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…

release: v2.0.26

release: v2.0.25

This release adds new billing and license controls for Copilot code review admins: Billing: Organization owners can bill Copilot code reviews from members with a Copilot license…

✨ Features Prompt for goose mode during first-time configure #12629 HTML session export with an interactive viewer #11977 🐛 Bug Fixes Adaptive thinking for Claude Sonnet and…

What does this PR do? conversation_items keyed rows on a global id , so an item id could belong to only one conversation. That allowed the silent re-parenting in #6703 , which…

Patch release on the release-1.0.x maintenance line. Fixes Require a compatible sentence-transformers on 1.0.x ( #6590 ) Build and release tooling Wait for published wheels…

Across recruiting, engineering, and operations, Oracle turns specialist knowledge into fast, repeatable workflows with ChatGPT Work and Codex.

With GPT-5.6, GPT-6 Astra, and GPT‑Image‑2.5, Pollo AI helps creators turn bold ideas into detailed images and cinematic video ads.

LegalOn cut estimated daily Codex costs by 65% while maintaining development speed. It matched Astra, Sol, and Luna to tasks and managed budgets strategically.

When a legacy GGUF which requires our llama.cpp patch set is loaded, we do a lazy conversion on disk to make it llama.cpp compatible. To support downgrades, we temporarily hold…

What's Changed server: proxy cloud usage and balance APIs by @drifkin in #18829 llama: fix clef head reads past 2GiB on windows by @Gigrise in #18777 cmd: remove account step…

A small release this week, mostly bug fixes and quality-of-life improvements. hf jobs stats now returns right away instead of streaming forever, concurrent downloads reliably use…

v2.2.0.rc0 pre-release

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…

The AI SDK moves together to one release line: ai 7.0.120 and every @ai-sdk/* package on @ai-sdk/provider-utils 5.0.50 (previously ai 7.0.79 with packages bumped one by one).…

@cline/shared@0.0.92

Chores ci: check that pull requests update the changelog docs: note that listing Claude Console spend limits is in early access internal: match the package version in uv.lock

Chores ci: check that pull requests update the changelog

Chores ci: check that pull requests update the changelog

Chores ci: check that pull requests update the changelog

What's Changed fix(ci): add missing loop in unassign-inactive-assignees workflow by @ugorla-dev in #29609 fix(core): enforce terminal user turn invariant and normalize request…

mlx: drop carried metal residency patch now that it is upstream ( #18854 )

Changes since langchain-fireworks==1.7.0 release(fireworks): 1.7.1 ( #41137 ) fix(fireworks): preserve reasoning in streaming and tool loops ( #41093 ) chore(deps): bump…

Changes since langchain-huggingface==1.2.2 fix(huggingface): use a supported Scaleway model in streaming test ( #41095 ) chore(deps): bump langgraph-sdk from 0.4.4 to 0.4.6 in…

Claude Haiku 5.5, Anthropic's newest lightweight model, is now generally available in GitHub Copilot. It is designed for fast, high-volume work like subagents, quick edits, and…

Secret protection should keep pace with the way you build software, whether you write code yourself or work with an AI agent. With our new purpose-built model, we're bringing…

Local sandboxing for GitHub Copilot is now generally available in GitHub Copilot CLI, the GitHub Copilot app, and VS Code sessions using Agent Host. Local sandboxes give…

This week's release includes Git tag creation, the ability to drag Terminal tabs into the Agent Panel, and pre-filling of the File Finder's search query with text selected in the…

This week's release includes the ability to preview JSONL and NDJSON files as tables. Features AI Added the agent.max_idle_retained_threads setting to control how many idle agent…

v1.23.x stable for @JosephTLyons

What's changed Added an optional subagent_type to background_tasks_changed task entries, so hosts can name each subagent's type without pairing with task_started Updated to…

What's changed 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…

0.0.18 (2026-10-07) Full Changelog: google-cloud-sdk-v0.0.17...google-cloud-sdk-v0.0.18

0.20.3 (2026-10-07) Full Changelog: vertex-sdk-v0.20.2...vertex-sdk-v0.20.3

0.132.0 (2026-10-07) Full Changelog: sdk-v0.131.0...sdk-v0.132.0 Features api: add claude-haiku-5-5 and typed computer and browser toolset tool calls ( 1fd8261 ) api: add…

Changes since cli==0.4.32 release(cli): 0.4.33 ( #9227 ) feat(cli): add --image-uri to deploy an already-pushed image ( #9222 ) feat(cli): add 'langgraph deploy listeners list' (…

College Planner is coming to ChatGPT for Teens to help students manage college applications, alongside new flashcards, quizzes, and a teen AI council.

Radisson partnered with Accenture to build a ChatGPT plugin using OpenAI technology, helping travelers find, compare, and book hotels while planning their trips.

GPT‑6 is rolling out globally in ChatGPT with Intelligent UI, delivering faster responses with visuals and interactive experiences you can explore and use directly.

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. For more information, see…

0.05x the base input price instead of 0.1x. Cache writes and all other prices are unchanged. See Prompt caching pricing. We've launched Claude Haiku 5.5 (claude-haiku-5-5), our…

https://code.visualstudio.com/updates/v1_141

Co-authored-by: github-actions[bot] 41898282+github-actions[bot]@users.noreply.github.com

What's Changed fix(cli): enforce read-only workspace settings in untrusted folders by @jvargassanchez-dot in #29583 fix(core): avoid duplicate tool response turns when resuming…

Release v5.19.0 New Model additions EmbeddingGemma2 EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture. It encodes text, images,…

grok-voice-transcribe-1.0 is deprecated and reaches end of life on October 2, 2026. All requests to that slug are routed to grok-voice-transcribe-2.0 at the same price, with…

What's Changed Update changelog by @Omar-V2 in #199 Fetch the correct version from PyPI in the release workflow by @Omar-V2 in #200 Update changelog by @Omar-V2 in #201 Add last…

Release Notes [2026-09-21] llama-index-agent-agentmesh [0.3.0] fix: resolve a ton of security alerts ( #22855 ) llama-index-agent-azure [0.4.0] fix: resolve a ton of security…

v0 now installs private packages from npm and custom registries using credentials stored as shared environment variables on Vercel. This makes it easier for teams to build with…