Follow us on LinkedIn, X, Bluesky
Release date: July 29, 2026
Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap
Welcome to the 1.131 release of Visual Studio Code. This release brings more visibility into running subagents, built-in dictation across the workbench, and a new hybrid Markdown editor.
-
Subagents: See a running subagent's model, elapsed time, and active tool call without opening its conversation.
-
Built-in dictation (Experimental): Dictate in chat, editors, and the terminal without installing the Speech extension.
-
Hybrid Markdown editor (Experimental): View, edit, and add agent-actionable comments to Markdown files in the Agents window.
Happy Coding!
VS Code is rolling out gradually to all users. Use Check for Updates in VS Code to get the latest version immediately.
To try new features as soon as possible, download the nightly Insiders build, which includes the latest updates as soon as they are available.
Agents
Agent host
As mentioned in our last few releases, we're rearchitecting how agent sessions work in VS Code around the agent host - a dedicated process that runs agent harnesses such as Copilot, Claude, and Codex, based on the Agent Host Protocol (AHP). Because a session lives in its own process, the same session can be connected to and rendered from multiple VS Code windows at once. The agent host's Copilot agent is powered by the Copilot SDK, which means that its behavior and functionality is aligned with the Copilot CLI, the standalone GitHub Copilot app, and other Copilot products.
We're actively developing the agent host and progressively rolling it out to users. To opt in, enable
chat.agentHost.enabled
This setting can be managed by your organization. Contact your administrator to change it. and then select an agent host harness from the harness dropdown. The screenshot below shows how to select the Copilot
harness on the agent host in the editor window:
You can learn more in our VS Code Agent Host architecture documentation. If you have any feedback or requests, please let us know by filing an issue.
More information about running subagents (Agents window)
When working on complex tasks, the agent can delegate tasks to subagents to run them in parallel in its own context window. You can now quickly see what a running subagent is doing without opening its conversation. In the Agents window, the main conversation shows the following information for each running subagent:
- The model used by the subagent
- How long the subagent has been running
- The tool that the subagent is actively calling
Select a running subagent to open its conversation in another chat, where you can review its full progress while the parent conversation remains available.
Chat
VS Code pet (Experimental)
A new highly experimental pet has been discovered in VS Code! Enter /vscode-pet
in chat to meet your new companion.
Editor Experience
Built-in dictation across VS Code (Experimental)
Setting: dictation.enabled This setting can be managed by your organization. Contact your administrator to change it., dictation.showTranscript , dictation.experimental.llmCleanup
To use dictation in VS Code, you no longer need to install the VS Code Speech extension. The built-in transcription service works in chat inputs, text editors, and the integrated terminal, with live text and controls suited to each surface. A single speech session and microphone selection are shared across all three surfaces, which prevents overlapping recordings and keeps dictated text in the intended location.
Built-in dictation uses the private, offline Nemotron model. The model downloads on first use and keeps audio on your device.
Use dictation.showTranscript to control whether the live transcript appears while you dictate. With dictation.experimental.llmCleanup enabled, Copilot refines your transcript as you speak by adding formatting and removing filler words. Transcript text is sent to a language model for cleanup. If cleanup is unavailable, VS Code keeps the raw transcript.
Platform support
The following platforms are supported for built-in dictation:
- Windows x64 and Arm64
- macOS on Apple silicon
- Linux x64 and Arm64 with glibc 2.34 or later
- Remote workspaces (because transcription runs on the local VS Code client)
The following platforms are not currently supported for built-in dictation:
- VS Code for the Web
- Intel-based Macs, 32-bit systems, and Arm32 systems
Support for more platforms and languages is a work in progress.
Hybrid Markdown editor (Experimental)
Setting: workbench.editor.markdownDefaultEditorInAgentsWindow
In this release, we introduce a new hybrid Markdown editor in the agents window. It lets you view Markdown files, edit them in-place, and add comments that an agent can act on.
By using Reopen Editor With you can switch between the text editor and this new Markdown editor, both in the Agents window and editor windows.
Accessibility
More control over terminal screen reader updates
Setting: terminal.integrated.accessibleViewPreserveCursorPosition
Screen reader users can read terminal output at their own pace while commands continue to produce output. Set
terminal.integrated.accessibleViewPreserveCursorPosition
to always
to preserve the cursor position in the terminal Accessible View, including when new content arrives. Existing true
and false
values continue to work.
Terminal live updates also use a non-interrupting ARIA status announcement instead of an assertive alert. Output remains available to screen readers without repeatedly interrupting other speech.
Terminal
Control the terminal resize dimensions overlay
Setting: terminal.integrated.resizeDimensionsOverlay.enabled
If you find the columns-by-rows overlay distracting when resizing the terminal, you can disable it with the terminal.integrated.resizeDimensionsOverlay.enabled setting. The overlay remains enabled by default, and setting changes apply immediately to open terminals without a restart.
Languages
Python
Python Environments is the default environment-management experience in VS Code Stable and Insiders after its rollout reached 100% of users. Review the Python Environments rollout details and tracking.
Python projects start faster and spend less time refreshing environments. Conda discovery is deferred until needed, concurrent environment scans are consolidated, and Pylance can use the last-known interpreter while a full refresh continues. #1600: Lazy-register Conda manager, #1598: Coalesce concurrent native finder refreshes with the same key, #1607: Return last-known environment when getEnvironment times out
Deprecated features and settings
None
Thank you
Contributions to vscode
:
- @accnops (Arthur Cnops): voice: make passive ptt_start the canonical hands-free narration fix PR #326405
- @bwateratmsft (Brandon Waterloo [MSFT]): Add a when clause context key for detecting if an extension is installed+enabled PR #326814
- @Kaidesuyoo (Kaidesuyo): fix performance regression caused by modern UI styles PR #325985
- @mirimadahmed (Mir): Fix voice barge in regression PR #326611
- @piyushmadan (Piyush Madan): Resolve execution subagent model by exact CAPI id before family fallback PR #324859
- @SimonSiefke (Simon Siefke)
- fix: memory leak in abstractTaskService PR #326934
- fix: memory leak in abstractRuntimeExtensionsEditor PR #326890
- fix: memory leak in terminalProcessManager PR #326930
- fix: memory leak in debugModel PR #327047
- fix: memory leak in terminalService PR #327156
- fix: memory leak in mainThreadTerminalService PR #327155
- @SixFive7 (Jori Huisman): Honor Explorer's
minItems
for the Windows taskbar jump list PR #318117 - @soreavis: Git - resolve the active notebook for Open Changes / Open File PR #326468
Issue tracking
Contributions to our issue tracking:
- @gjsjohnmurray (John Murray)
- @RedCMD (RedCMD)
- @IllusionMH (Andrii Dieiev)
- @albertosantini (Alberto Santini)
We really appreciate people trying our new features as soon as they are ready, so check back here often and learn what's new.
If you'd like to read release notes for previous VS Code versions, go to Updates on code.visualstudio.com.
Facts Only
Visual Studio Code version 1.131 was released on July 29, 2026.
Available downloads include Windows (x64, Arm64), Mac (Universal, Intel silicon), and Linux (deb, rpm, tarball, Arm, snap).
A new agent host process based on the Agent Host Protocol (AHP) supports Copilot, Claude, and Codex.
Running subagents now display the model used, elapsed time, and active tool calls in the Agents window.
Built-in dictation is available for Windows x64/Arm64, macOS Apple silicon, and Linux x64/Arm64 (glibc 2.34+).
Built-in dictation utilizes an offline Nemotron model.
A hybrid Markdown editor allows in-place editing and agent-actionable comments in the Agents window.
The `/vscode-pet` command introduces an experimental companion in chat.
Python Environments is now the default environment-management experience for all users.
New accessibility settings allow for preserving cursor position in the terminal's Accessible View.
A setting to disable the terminal resize dimensions overlay was added.
The release includes memory leak fixes in the abstractTaskService, abstractRuntimeExtensionsEditor, terminalProcessManager, debugModel, terminalService, and mainThreadTerminalService.
Executive Summary
Visual Studio Code 1.131 introduces a significant architectural shift toward an "agent host" model. By moving agent sessions—including Copilot, Claude, and Codex—into a dedicated process via the Agent Host Protocol, the software now allows a single session to be rendered across multiple windows simultaneously. This evolution is accompanied by increased transparency for subagents, providing real-time visibility into their models and active tool calls without requiring the user to switch conversations.
The update further integrates AI-driven productivity through a new hybrid Markdown editor for agent collaboration and an experimental built-in dictation system. This dictation service operates offline using the Nemotron model to ensure data privacy, though an optional LLM-based cleanup feature exists for refining transcripts. While these features are expanding, platform support remains fragmented; Intel-based Macs and web-based versions of the editor do not currently support dictation. Performance optimizations for Python environments and various memory leak fixes complete the release, aiming for a more stable and responsive development experience.
Full Take
The strongest version of this update is a leap toward "Agentic IDEs," where the editor is no longer just a text manipulator but a coordinator of autonomous sub-processes. By decoupling the agent from the main UI thread and utilizing a dedicated host protocol, the environment is transitioning from a tool used by a human to a workspace shared by a human and a fleet of specialized AI agents.
The paradigm here is the "invisible transition." By integrating dictation via an offline model and embedding agent-actionable comments directly into Markdown, the friction between human intent and machine execution is being systematically removed. The shift toward a dedicated "Agent Host" suggests a future where the IDE is merely a frontend for a persistent, background AI operating system that manages codebases independently of the user's active window.
The cost of this convenience is a deepening dependency on specific AI ecosystems. While the protocol allows for different harnesses (Claude, Codex), the tight alignment with the Copilot SDK ensures that the user experience remains tethered to a specific corporate AI logic. We are seeing the "platformization" of the developer's thought process, where the tools don't just assist the work but define the workflow.
Patterns detected: none
Root Cause: The narrative is driven by the industry-wide push toward "Agentic Workflows," moving away from simple chat-based LLMs toward autonomous agents that can execute tools and manage their own state.
Implications: Human agency may shift from "writing code" to "managing agents." While this increases productivity, it risks a deskilling of the developer if the underlying logic of the agent's tool-calls remains opaque.
Bridge Questions: If the agent host becomes the primary driver of development, how does the role of the "senior architect" change? At what point does the "hybrid editor" stop being a tool for humans and start being a communication protocol between agents?
Counterstrike Scan: A coordinated campaign to push this narrative would emphasize the "inevitability" of agentic workflows to pressure developers into adopting specific AI subscriptions. This content is a standard technical release note and does not match that pattern.