Add A2A server

[Kludex]

This PR implements the FastA2A - an easy way to serve an agent using the A2A protocol.

We need to make some decisions here.

High level decisions

• Should this code live in Pydantic AI? I'm happy to move it away - it may be better.
• Currently there's a client in the A2A repository, but I didn't like their work. Also, they didn't publish on PyPI...
• On MCP there's an inspector client which makes life easier. This protocol still doesn't have such a thing. It makes the experience of developing A2A servers poor.

Low level decisions

• Is the architecture right? Something feels a bit odd regarding the worker/runner, and the fact that I need to pass the agent on the FastA2A. Something is wrong here.

Checklist

• Tests
• Documentation

---

Opinions A2A

Honestly, after developing this, I'm not sure if the protocol will thrive. It seems the specification was written in a hurry, it misses a lot of examples, and it doesn't specify how the workflows should be.

To be more concrete, let's say we want to send a task. It's (supposedly) the simplest workflow. When you send a task, you have some options:

1. You can execute the agent, and either send a "complete", "failed" or "input-required" response.
2. You can schedule a task on the background, and send back the task id and a status "submitted".

How do we choose? Thinking about the best HTTP practices, ideally, we should send back an id, and run the task in the background... And that's what I did. That's more complicated tho, and also, is it really necessary? I can't make a simple developer-facing code without making this decision, because it implies in infrastructure changes.

In any case, I've developed this incomplete PR, which I hope we can discuss and refine in the next days.

[Kludex]

Need to add the other classes here.

[github-actions]

Docs Preview

commit:	068a9ac
Preview URL:	https://87ecd93a-pydantic-ai-previews.pydantic.workers.dev

[Kludex]

Suggested change

	app = FastA2A(agent)
	app = FastA2A.from_agent(agent)
	app = FastA2A.from_graph(graph, get_first_node: Callable[[list[Message], BaseNode])

[hyperlint-ai]

PR Change Summary

Implemented the FastA2A library to facilitate the development of A2A servers, enhancing interoperability between AI agents.

• Introduced the FastA2A library for serving agents using the A2A protocol
• Added comprehensive documentation for the A2A protocol and FastA2A usage
• Outlined design components including TaskManager, Worker, and Runner

Added Files

• docs/a2a.md

---

How can I customize these reviews?

Check out the Hyperlint AI Reviewer docs for more information on how to customize the review.

If you just want to ignore it on this PR, you can add the hyperlint-ignore label to the PR. Future changes won't trigger a Hyperlint review.

Note specifically for link checks, we only check the first 30 links in a file and we cache the results for several hours (for instance, if you just added a page, you might experience this). Our recommendation is to add hyperlint-ignore to the PR to ignore the link check for this PR.