Release notes from 42 developer and AI products, in one archive.

perf(desktop): keep the shell mounted under settings, cheaper mounts by @charlesvien in https://github.com/PostHog/posthog/pull/91362 perf(desktop): stop whole-document restyles and svg spinner churn by @charlesvien in https://github.com/Po

feat(context-layer): add a Dreams tab to the context page by @k11kirky in https://github.com/PostHog/posthog/pull/90370 fix(tasks): let repo-less warm requests carry a github integration by @JakeRuth in https://github.com/PostHog/posthog/pu

feat(desktop): render mermaid diagrams in markdown artifacts by @charlesvien in https://github.com/PostHog/posthog/pull/91349 fix(desktop): serve GitHub comment images from the disk cache by @charlesvien in https://github.com/PostHog/postho

feat(desktop): add profile picture to general settings by @charlesvien in https://github.com/PostHog/posthog/pull/91323 fix(desktop): ship the dark icon, fix the boot race, move ci to depot by @charlesvien in https://github.com/PostHog/post

fix(tasks): query hogpanion via sudo in the golden smoke test by @Gilbert09 in https://github.com/PostHog/posthog/pull/91290 feat(desktop): pick a cloud environment or image, and star a favorite by @puemos in https://github.com/PostHog/post

MiniMax H3 and H3 Max are 50% off on AI Gateway from August 30 through September 13, in partnership with MiniMax.The discount covers requests billed through AI Gateway, at every duration and in every aspect ratio the model supports.H3 gener

fix(desktop): suppress toasts for open task panels by @dmarticus in https://github.com/PostHog/posthog/pull/91075 chore(deps): Update @posthog/react-native-plugin to 2.5.1 by @posthog-js-upgrader in https://github.com/PostHog/posthog/pull/9

feat(desktop): run local codex sessions on the user's own ChatGPT subscription by @puemos in https://github.com/PostHog/posthog/pull/89077 fix(tasks): keep workflow AI task runs open so the convo can go on when triggered from slack by @mayt

fix(desktop): correct GLM 5.3 Flash cost multiplier by @tatoalo in https://github.com/PostHog/posthog/pull/90743 fix(desktop): always show at least one browser tab by @adamleithp in https://github.com/PostHog/posthog/pull/90105 fix(mcp): de

feat(desktop): replace the loading gif with an animated SVG logo by @charlesvien in https://github.com/PostHog/posthog/pull/90618 Downloads macOS Package Architecture Download Blockmap SHA-256 DMG Apple Silicon (arm64) PostHog-Desktop-0.61.

Hy4 Preview from Tencent is now available on AI Gateway.Hy4 Preview is an open-source Mixture-of-Experts model with 770B total parameters and 49B active per token, aimed at long-horizon coding, document analysis, game development, and scien

You can now create eve agents directly from the Vercel dashboard, giving you a deployed agent that you can chat with right away. The builder scaffolds the agent, creates a private Git repository with its files, and deploys it as a new Verce

The Vercel CLI now provides dedicated commands for managing DNS records, domains, and projects. This brings more of the functionality available through the Vercel dashboard and API to the terminal, where it can be used interactively, in scr

AI Search now supports @cf/zai-org/glm-5.3-flash for text generation. The model has a 1,048,576-token context window and runs on Workers AI. To configure the model for an AI Search instance, refer to Supported models.

A new GA release for the macOS Cloudflare One Client is now available on the stable releases downloads page. This hotfix resolves an issue where a small but noticeable percentage of DNS queries fail across platforms.

@cf/zai-org/glm-5.3 is now available on Workers AI. It is Z.ai's flagship agentic coding model, built for long-running, tool-driven development workflows rather than single-turn chat. GLM-5.3 uses the same base model as GLM-5.2, with every

Durable Objects can have up to ten distinct Dynamic Workers with in-flight requests, increased from four. This limit applies across all concurrent requests to the same Durable Object because they share an input/output (I/O) context. Other W

Features api: add compute_units to Responses and Chat Completions usage (#3749) (52421d1) Bug Fixes auth: harden X.509 workload identity integration (#3740) (fc3ad6c) Chores deps-dev: bump @stdy/cli from 0.22.1 to 0.22.2 (#3719) (4f5598c) d

August 2026 brought more control over how GitHub Copilot reasons, which models you use, how teams share specialized agents, and when you ask for a code review. Highlights Here’s what’s new with GitHub Copilot in Visual Studio 2026. Check th

This week’s updates give you more control over how Copilot runs, from team sessions in Slack and Teams to customization across the app, CLI, and your IDE. GitHub Copilot in Slack and Microsoft Teams Turn team conversations into shared agent

To provide a strong, consistent Copilot experience, we’re making three separate, upcoming changes to Copilot policies and billing. Please review the upcoming updates to understand what may impact you. Reopening Copilot Business and Enterpri

Bug Fixes core: Allow a domain-restricted credential to work in its own node (#37248) (1166741)

Minor Changes feat: export RenderOutput, SyncRenderOutput, Csp and Sha256Source from svelte/server (#18648) feat: add has function to createContext (#18472) feat: support defaultValue on <select> (#18591) feat: add getOrInsert/getOrInsertCo

Build from commit 2f44a500a9828b82395c697829a9940f1f374d65

You can now run Claude Managed Agents with Chat SDK.Claude Managed Agents handles the agent loop server-side, including the model, tools, session state, and sandboxed web research. That means you can ship a Slack research bot built on Claud

The AI SDK harness layer now supports Cursor through the official @ai-sdk/harness-cursor adapter. The harness layer lets your application run different coding agents through the same HarnessAgent interface, so you can switch agents without

The Deployments page now has redesigned filters that make it faster to find a specific deployment. You can: Apply suggested filters for common searches. Type to find an option instead of scrolling through the list.Describe what you’re looki

The idea of orchestrating long-running, stateful logic on top of unreliable, stateless infrastructure isn't new. We've had message queues, job runners, microservice choreographies, and full-blown workflow engines for a long time. What we ne

Ling 3.0 Flash Fin from Inclusion AI is now available on AI Gateway and free to use through September 25. Ling 3.0 Flash Fin is a finance-focused version of Ling 3.0 Flash. It has a 256K-token context window, produces up to 32K output token

Features api: make function call output call IDs optional (#3738) (c74501d)

We’re making it easier to keep labels organized and find the right one, especially in repositories with long and growing label lists. Suggested Labels You can now find the right label faster with suggestions based on what a repository has b

Copilot code review can now review two types of pull requests it didn’t cover before: Reviews requested automatically on pull requests authored by bots, including Copilot cloud agent Very large pull requests Additionally, you can now submit

As of August 28, 2026, GitHub Classroom is now deprecated in favor of our selected partner solutions. The GitHub Classroom website, APIs, and related services have now been decommissioned. However, any GitHub user accounts, repositories, an

Starting October 1, 2026, checks, workflow runs, and statuses will be governed by the same Actions retention setting that already controls how long artifacts and logs are kept, with a default of 90 days. Until now, checks, workflow runs, an

You can now automatically close all open issues, discussions, and pull requests authored by a user when you block them from your personal account or organization. To use this option, select Close content authored by this user in the block d

You can now opt individual plugin marketplaces into automatic updates by setting autoUpdate: true on an extraKnownMarketplaces entry in enterprise managed settings. Supported clients automatically check the marketplace and update installed

You can now create personal keys and service account keys in the Claude Console. They act as you or as a service account, with the same permissions, and stop working when the linked account is removed from an organization. This lets organiz

For stable releases, please refer to CHANGELOG.md for details. For pre-releases, please refer to CHANGELOG.md of the minor branch.

Features api: beta files/skills namespaces use GA shapes; drop dated beta header pins (9df4565) Bug Fixes aws,bedrock: sign raw request bytes so binary file uploads work (#531) (f50e910) ci: resolve assignment aliases in detect-breaking-cha

Release 2026-08-27 16:07 Changes Fix preact-query/useQueries: keep unsubscribed idle (#11315) (6c27607d7) by @sukvvon Packages @tanstack/angular-query-experimental@5.102.8 @tanstack/eslint-plugin-query@5.102.8 @tanstack/lit-query@0.2.20 @ta

Release 2026-08-27 08:32 Changes Fix preact-query: propagate falsy errors to the error boundary (#11309) (67fddee63) by @sukvvon Packages @tanstack/angular-query-experimental@5.102.7 @tanstack/eslint-plugin-query@5.102.7 @tanstack/lit-query

Patch Changes Updated dependencies []: @tanstack/query-core@5.102.8

Patch Changes Updated dependencies []: @tanstack/query-core@5.102.7

Patch Changes Updated dependencies []: @tanstack/query-devtools@5.102.8 @tanstack/vue-query@5.102.8

Patch Changes Updated dependencies []: @tanstack/query-devtools@5.102.7 @tanstack/vue-query@5.102.7

Patch Changes Updated dependencies []: @tanstack/query-core@5.102.8

Patch Changes Updated dependencies []: @tanstack/query-core@5.102.7