Fixes: https://a2a-protocol.org/latest/tutorials/python/6-interact-with-server/#understanding-the-client-code Sample update: #508
4.7 KiB
6. Interacting with the Server
With the Helloworld A2A server running, let's send some requests to it. The SDK includes a client (A2AClient) that simplifies these interactions.
The Helloworld Test Client
The test_client.py script demonstrates how to:
- Fetch the Agent Card from the server.
- Create an
A2AClientinstance. - Send both non-streaming (
message/send) and streaming (message/stream) requests.
Open a new terminal window, activate your virtual environment, and navigate to the a2a-samples directory.
Activate virtual environment (Be sure to do this in the same directory where you created the virtual environment):
=== "Mac/Linux"
```sh
source .venv/bin/activate
```
=== "Windows"
```powershell
.venv\Scripts\activate
```
Run the test client:
# from the a2a-samples directory
python samples/python/agents/helloworld/test_client.py
Understanding the Client Code
Let's look at key parts of test_client.py:
-
Fetching the Agent Card:
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/test_client.py:A2ACardResolver"The
A2ACardResolverclass is a convenience. It first fetches theAgentCardfrom the server's/.well-known/agent-card.jsonendpoint (based on the provided base URL) which is then used to initialize the client. -
Initializing the Client & Sending a Non-Streaming Message:
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/test_client.py:message_send"- A
ClientFactorycreates a non-streaming client based on the fetched card. - We construct a
Messageobject usingRole.ROLE_USERandPartfor the content. - This is wrapped in a
SendMessageRequest. - The client's
send_messagemethod returns an async generator that yields a sequence ofTaskevents from the agent.
- A
-
Initializing the Client & Sending a Streaming Message:
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/test_client.py:message_stream"- A new streaming client is created via
ClientFactoryconfigured withstreaming=True. - We again call
send_message(which now handles both streaming and non-streaming under the same method name, based on theClientConfigand agentcapabilities). - The response dynamically yields
Taskevents as they are streamed over the network.
- A new streaming client is created via
Expected Output
When you run test_client.py, you'll see in protobuf text format outputs for:
- The non-streaming response (a single final
tasklog detailing the history, status, and the generated artifact containing the "Hello, World!" text). - The streaming response (multiple discrete events including the initial
task, astatus_update, and a finalartifact_updatecontaining the "Hello, World!" text).
The id fields in the output will vary with each run.
// Non-streaming response
task {
id: "xxxxxxxx"
context_id: "yyyyyyyy"
status {
state: TASK_STATE_COMPLETED
}
artifacts {
artifact_id: "zzzzzzzz"
name: "result"
parts {
text: "Hello, World!"
}
}
history {
message_id: "vvvvvvvv"
context_id: "yyyyyyyy"
task_id: "xxxxxxxx"
role: ROLE_USER
parts {
text: "Say hello."
}
}
history {
message_id: "wwwwwwww"
role: ROLE_AGENT
parts {
text: "Processing request..."
}
}
}
// Streaming response
task {
id: "xxxxxxxx-s"
context_id: "yyyyyyyy-s"
status {
state: TASK_STATE_SUBMITTED
}
history {
message_id: "vvvvvvvv"
context_id: "yyyyyyyy-s"
task_id: "xxxxxxxx-s"
role: ROLE_USER
parts {
text: "Say hello."
}
}
}
Response chunk:
status_update {
task_id: "xxxxxxxx-s"
context_id: "yyyyyyyy-s"
status {
state: TASK_STATE_WORKING
message {
message_id: "zzzzzzzz-s"
role: ROLE_AGENT
parts {
text: "Processing request..."
}
}
}
}
Response chunk:
artifact_update {
task_id: "xxxxxxxx-s"
context_id: "yyyyyyyy-s"
artifact {
artifact_id: "wwwwwwww-s"
name: "result"
parts {
text: "Hello, World!"
}
}
}
Response chunk:
status_update {
task_id: "xxxxxxxx-s"
context_id: "yyyyyyyy-s"
status {
state: TASK_STATE_COMPLETED
}
}
(Actual IDs like xxxxxxxx, yyyyyyyy, zzzzzzzz, vvvvvvvv, wwwwwwww will be different UUIDs/request IDs)
This confirms your server is correctly handling basic A2A interactions with the updated SDK structure!
Now you can shut down the server by typing Ctrl+C in the terminal window where __main__.py is running.