Coding sessions: environments, browser use, and updated pricing
By Steven Van ·
Linear Agent can now set up, run, and test your code before returning its work.
Coding sessions in Linear can now set up, run, and test code before handing it back, rather than returning work for a person to run first. Linear also cut pricing for coding sessions and made costs easier to track.
- Configurable environments: sessions detect and install the toolchains and dependencies a task needs, with broader out-of-the-box support for Python, Ruby, Go, and more. Teams can pin runtime versions, add setup scripts, and define environment variables by creating an environment in settings.
- Browser testing: once the app is running, the agent opens it, navigates through a flow, and verifies the implementation, capturing before-and-after screenshots. If it finds a problem, it can fix it, rerun the test, and return the work with that validation complete.
- Updated pricing: coding sessions now charge for model usage at the provider's published rates with no markup, plus sandbox runtime at $0.25 per 20-minute block. The usage dashboard breaks down token usage and cost by model, and admins can set workspace-wide or per-user spend limits that reset daily, weekly, or monthly.
Details on both features and on AI credit pricing are in the full changelog entry.
Linear
The issue tracking and project management tool built for modern software teams — fast, keyboard-driven, with a built-in agent that can run workflows for you.
View Linear →