Skip to content

AI Agent Development

VS Code 1.145 Expands Remote Agent Workflows and Nested Coding Agent Harness Controls

Visual Studio Code 1.145 introduces remote browser support, nested coding agent harnesses, and local cron-driven workspace automations. These updates let engineering teams validate agent changes inside integrated dev previews without manual browser switching.

Editorial illustration about VS Code 1.145 Expands Remote Agent Workflows and Nested Coding Agent Harness Controls in AI Agent Development.

Developer tooling environments must handle more than static code generation as AI coding agents take on complex multi-step tasks. Engineers need integrated feedback loops to inspect agent actions without breaking focus or context.

Visual Studio Code 1.145 addresses this operational friction by expanding remote agent workflows, adding nested session harnesses, and supporting scheduled workspace automations.

In short

  • Visual Studio Code 1.145 introduces remote browser and canvas previews directly inside the Agents window to streamline change validation.
  • Nested chat sessions can now run independent coding agent harnesses, enabling secondary model reviews without splitting conversation threads.
  • Local workspace automations gain five-field cron scheduling and custom agent integration for recurring background tasks.
  • Engineering teams must manage verbosity settings and file-exclusion lists to keep agent memory usage and search indexes clean.

Remote Browser Integration and Preview Canvases

Validating agent changes typically forces developers to leave the editor and open an external browser. Version 1.145 integrates a remote browser directly into the Agents window through dedicated configuration settings.

Builders can load dev server previews locally, review modifications made by an active agent, and supply immediate feedback in one interface. Remote canvases also arrive in preview to support real-time architectural inspections.

Nested Sessions and Independent Harness Configuration

Complex refactoring tasks often benefit from a secondary review by a specialized model. The latest release permits nested chat sessions to operate on a different coding agent harness than their parent session.

Each nested thread retains its own model selection, agent definition, and permission boundaries. This architecture allows developers to ask a second agent to check code quality without fracturing the original context window or spawning disconnected chat logs.

Scheduled Local Automations and Session Controls

Background workspace tasks require reliable execution triggers rather than manual invocation. Local automations now support five-field cron schedules alongside custom workspace agents for routine maintenance.

Additional updates include agent verbosity controls for balancing concise responses against deep technical explanations, alongside precise file-exclusion settings that preserve search performance across large repositories.

Adopting integrated remote canvases and nested agent harnesses reduces manual handoffs during code review cycles. Engineering teams can update to version 1.145 using the built-in update check.

Sources

Similar posts

PROJECT INQUIRY

Automate a business process?

Tell us which process currently takes too much time or manual effort. Together we examine what an executable workflow for it looks like, and reply personally.

Your information is treated confidentially in accordance with our Privacy policy.