Skip to main content
A complete, runnable example of putting a wire protocol in front of Chat: serve a messages-style task as an A2A endpoint, so any A2A client — including another LLM using it as a tool — can hold a conversation with your environment. Chat is protocol-agnostic (see Chat); the A2A layer is a reference server kept outside the SDK on purpose. Copy and adapt it from cookbooks/a2a-chat.

​
The pieces

FileWhat it does
server.pyA2A server: one Chat (conversation) per A2A context, agent card, citations artifact
client.pyMinimal A2A client: send messages, print replies
llm_client.pyLLM-fronted client: an OpenAI model decides when to call the A2A agent as a tool
chat_env.pySample chat environment with messages-style tasks to serve

​
The environment

A chat-style task takes the running conversation as a messages parameter and yields it as the prompt:
chat_env.py
from mcp.types import PromptMessage
from hud.environment import Environment

env = Environment(name="chat")

@env.template()
async def chat_simple(messages: list[PromptMessage]):
    yield messages   # the conversation so far is the prompt
    yield 1.0

​
Run it

From cookbooks/a2a-chat (uv resolves the dependencies on first run): 
# Terminal 1: serve the bundled chat task (spawns chat_env.py per turn)
uv run server.py

# Terminal 2: talk to it
uv run client.py            # plain client
uv run llm_client.py        # LLM-fronted client
The server publishes an agent card at /.well-known/agent-card.json and accepts A2A messages at the root endpoint. Each A2A context gets its own Chat, so concurrent conversations stay independent. Configuration is via env vars: HUD_MODEL picks the agent’s model (gateway, needs HUD_API_KEY), HUD_TASK/HUD_ENV pick the task row, HUD_SOURCE spawns a different env source, and HUD_ENV_URL attaches each turn to an already-served control channel (e.g. hud serve chat_env.py → HUD_ENV_URL=tcp://127.0.0.1:8765) instead of spawning.

​
See also

Chat

Integrations