VS Code 1.146 adds an inbox for AI agent sessions and model comparisons

Nov 13, 2026
The update also lets chats open in their own windows and deprecates the Local agent harness, which goes in February 2027.

Microsoft has released Visual Studio Code 1.146, which adds tools for developers running several AI coding agents at once, according to the release notes. An experimental Inbox mode shows, across all projects, which agent sessions need attention, which are still running and which are ready to merge, and lets users snooze or set aside the rest.

The release also improves a preview feature for comparing results from different models, now including Copilot Fusion, or letting an agent run the comparisons, and lets users open chats in separate windows alongside their editors and terminals. The older Local agent harness is deprecated and will be removed in February 2027 in favour of the GitHub Copilot harness, which has been the default for new sessions since version 1.143.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

Guide
AI app builders

AI app builders

Tools that turn a description into a working web or mobile app, and the platforms companies use to build internal tools with AI

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.