liveBook · Manning

A2A message

As explained in Build a Multi-Agent System (from Scratch)

An A2A message is a communication between an agent and a client containing one or more content parts.

An A2A message carries content between a client and an agent. In a task lifecycle, the client sends one to a remote agent with instructions; messages generally support self-contained interactions. Each message contains one or more Parts, and each Part holds text, raw bytes, a file URI, or JSON data. A message also has a role, or sender. section 10.1.3 section 10.2.2

Hailstone task request

A client can send a message with one text Part: “Compute the Hailstone sequence starting at 6.” section 10.1.3

Figure 10.5 Simplified UML class diagram of the important A2A elements used in a task lifecycle (this is different from our typical UML class diagrams, which we use as build plans for our implementations)

Use the diagram to see how Message relates to Part, Task, and Artifact. section 10.1.3

How Build a Multi-Agent System (from Scratch) covers it

How deep it goes
Defines Message through its Parts and role, then places it in the task lifecycle.
Examples
Uses a text instruction to request the Hailstone sequence starting at 6.
What you can do after
Apply it via the A2A Python SDK to send a task message to a remote agent.
How it connects
Relates Message to Part, Task, and Artifact in the A2A task lifecycle.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build a Multi-Agent System (from Scratch). The section links point to the parts of the book it draws on.