正在加载视频...

视频加载失败

The latest release of Visual Studio Code includes the new "Agent HQ" - aka the Agent Sessions view. Here's a quick rundown plus a UI tweak you can make for a "unified" agent layout...

11,662 次观看 • 11 个月前 •via X (Twitter)

10 条评论

Burke Holland 的头像
Burke Holland11 个月前

More on Agent Sessions...

Big Bruno 的头像
Big Bruno11 个月前

@code Try and rebuild vs code in rust it will be too slow to handle modern asynchronous development

Burke Holland 的头像
Burke Holland11 个月前

@code Nahhhh

Malitha Sandaruwan 的头像
Malitha Sandaruwan11 个月前

@code we can add Claude code as agent ?

Burke Holland 的头像
Burke Holland11 个月前

@code I like the sound of that!

CrazyAI Tech 的头像
CrazyAI Tech11 个月前

@code It looks really tempting. I’ll give it a try later. The background agent looks great.

Seth Rose 的头像
Seth Rose10 个月前

@code @burkeholland Am I crazy? I no longer see the "Agent Sessions" or Agent HQ icon in VS Code Insiders. I only see "Sessions" in the sidebar of the Chat window. The only options shown are Stacked & Side by Side, so this tip no longer works.

Azerty 的头像
Azerty11 个月前

@code how to see the subagents in this view ?

Burke Holland 的头像
Burke Holland11 个月前

@code Subagents run in the chat window. They aren't background, they are just isolated context. Still single threaded in the chat tho.

Azerty 的头像
Azerty11 个月前

@code thx , the last ide from google fix this bad behavior with // agents tasks

相关视频

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

Santiago

17,438 次观看 • 4 个月前