Releasesby GlyphIssue discussion summaries
Discussion summaries now appear on issues with substantial activity. Read these summaries to understand what's happened in an issue without reading every comment. Summaries capture decisions, blockers, debates and their resolutions, and key people involved. When new comments are posted, summaries automatically regenerate to reflect changes.
Also shipped Oct 2, 2025Linear in October 2025 →
Bring your Vercel project to Replit (in minutes)
Users can now import Vercel projects into Replit. The Replit Agent automates the setup process, including environment variable configuration and deployment.
Cloudflare Fundamentals, Access - Fine-grained Permissioning for Access for Apps, IdPs, & Targets now in Public Beta
Fine-grained permissions for Access Applications, Identity Providers (IdPs), and Targets is now available in Public Beta. This expands our RBAC model beyond account & zone-scoped roles, enabling administrators to grant permissions scoped to individual resources. What's New Access Applications ↗ : Grant admin permissions to specific Access Applications.
Updated support for OpenAI GPT-OSS (gpt-oss-120b) - Tool calling with strict: true (constrained decoding) -...
Updated support for OpenAI GPT-OSS (gpt-oss-120b) Tool calling with strict: true (constrained decoding) Response format with json_schema when using strict=true Response format with json_object when using strict=true tool_choice: none Updated JSON Schema limitations: Nested levels increases from 5 to 10 Max properties increases from 100 to 500 Enabled...
Introducing Flux: Conversational Speech Recognition to Solve the Biggest Problem in Voice Agents – Interruptions
Flux is here: the first real-time Conversational Speech Recognition model built for voice agents. Solve interruptions, cut latency, and ship natural conversations faster than ever. Deepgram is proud to announce the release of Flux , the first speech recognition model that knows when someone is actually done talking.
Workers AI - New Deepgram Flux model available on Workers AI
Deepgram's newest Flux model @cf/deepgram/flux is now available on Workers AI, hosted directly on Cloudflare's infrastructure. We're excited to be a launch partner with Deepgram and offer their new Speech Recognition model built specifically for enabling voice agents. Check out Deepgram's blog ↗ for more details on the release.
Workers Analytics Engine, Workers - Workers Analytics Engine adds supports for new SQL functions
You can now perform more powerful queries directly in Workers Analytics Engine ↗ with a major expansion of our SQL function library. Workers Analytics Engine allows you to ingest and store high-cardinality data at scale (such as custom analytics) and query your data through a simple SQL API.
More from LinearEvery Linear release →
Label descriptions and archiving
Label descriptions and archiving Labels let you organize issues and projects in ways specific to your team or workspace. They can be used to define custom views and dashboards, or in Triage and SLA rules. We've made significant improvements to label functionality and management.
Mobile app redesign
We’ve refreshed our iOS and Android apps with a new visual design system. Both now use a custom frosted glass material that adds depth and contrast to the UI. Navigation has been rebuilt with a new bottom toolbar for quick access to core workflows. You’ll also now find a "Create Issue" button at the top of every screen.
Linear agent for Slack
Creating issues has never been easier. Mention @Linear in discussions on Slack, and the Linear agent will create issues informed by your conversation's context. Use natural language to specify issue details or simply let the agent infer what's needed. Linear agent for Slack is available now on all plans.
GitHub Copilot agent
GitHub Copilot users can now work with the GitHub Copilot agent directly within Linear. Delegate any issue directly or mention GitHub Copilot in a comment, and the agent will use the full issue context to start an implementation in a draft PR. You can follow Copilot's progress on the Linear issue or on the PR in GitHub.
Pulse on mobile
Pulse is now available in Linear's iOS and Android apps. Stay up-to-date on the progress of your projects and initiatives, no matter where you are. Pulse brings relevant updates from across your Linear workspace into a single unified feed, so you can quickly see what's happening.
Form templates
Form templates are a new type of issue template that support form fields. Use these templates to collect specific issue details upfront so work is actionable from the start.
OpenAI Codex agent
OpenAI Codex users can now delegate issues directly to the Codex agent without leaving Linear. Codex can answer questions about your codebase, fix bugs, or take a first pass at issues in your Triage queue. Assign issues to the Codex agent, and it will use the full issue context, automatically choose the right repo, and start working on a solution.
Linear agent for Intercom, Zendesk, Gong
The Linear agent can now handle the tedious work of turning customer conversations into actionable issues. Available through our Intercom, Zendesk, and Gong integrations, the agent parses conversations and automatically files issues with the relevant details.