In this demo, we build, run and evaluate an agentic system with Akka and Claude Code. It contains agents, memory, endpoints, orchestration, and streaming. The system is deployed as a 3 node cluster for resilience, and then deployed into GCP and AWS for multi-region failover and disaster recovery.
Use akka-context folder that contains Akka SDK documentation and check Agent
docs.
Create an Akka SDK agent named `GreetingAgent` that assists users in learning
greetings in different languages.
- **Input:** A string question.
- **Output:** Returns an `Effect<String>`.
- method with name `ask`
- Do not perform any environment variables check.
- Do not add JavaDoc annotations
- place it into com.example.application package
- system message should be a static variable
- **Guidelines for system prompt:**
- The user must provide a language.
- Always append the language used in parentheses in English (e.g., "Bonjour
(French)").
- At the end of each response, append a list of previous greetings used in
the current session.Use akka-context folder that contains Akka SDK documentation and check Agent
integration test docs.
Develop only one integration test for `GreetingAgent` in the `com.example`
package, named `IntegrationTest`.
- Include a `TestModelProvider` to mock the model with a fixed response.
- Ensure all necessary classes are properly imported.Use akka-context folder that contains Akka SDK documentation and check Endpoint
docs and how to call an Agent.
Implement an HTTP endpoint `GreetingAgentEndpoint` with the following
specifications:
- **Base path:** `/chat`
- **Endpoint:** POST `/ask`
- **Request:** Accepts a JSON record `QueryRequest` with fields `String userId`
and `String question`.
- Put the QueryRequest in the GreetingAgentEndpoint class
- The agent should use `userId` as the sessionId and `question` as the
user message.
- add acl for all accessUse akka-context folder that contains Akka SDK documentation and check
MCPEndpoint docs
Create an MCP server endpoint named `UserNameMcpEndpoint` for retrieving
user's name based on `userId`.
- Place the implementation in the `com.example.api` package.
- Provide a mock implementation that returns a random name for each query.
- add all needed annotations (class and method)
- use MCP Tool annotations with all required parameters including the
McpEndpoint annotationUse akka-context folder that contains Akka SDK documentation and check how
to configure MCP tools for an Agent
Update the `GreetingAgent` to display the user's name during the first
interaction, for example: "Hello <user name>!".
- Configure GreetingAgent to use `UserNameMcpEndpoint` as an MCP tool. No need
to use AllowedToolNames. Use the service name specified by the `artifactId`
in `pom.xml`.
- set `userId` from context().sessionId().
- Add the `userId` to the user message in the following format:
"userId:<userID>;question:
- update system prompt accordingly Use akka-context folder that contains Akka SDK documentation and check Agent
and Endpoint streaming support.
Replace the `GreetingAgent`'s `greet` method with a streaming response.
- Update the `GreetingAgentEndpoint`'s `ask` endpoint to use the streaming
response from `GreetingAgent` and wrap it with Server-Sent Events (SSE),
returning an `akka.http.javadsl.model.HttpResponse`.
- Remove all non-streaming methods from both `GreetingAgent` and
`GreetingAgentEndpoint`.
- Update the integration test to use the streaming agent. Do not modify the
`TestModelProvider`.
**Example usage in the integration test:**
var tokenStream = componentClient
.forAgent()
.inSession(sessionId)
.tokenStream(HelloWorldAgent::streamGreet)
.source(userGreeting);
// Run the stream and collect the tokens into a List
List<String> tokens = tokenStream
.toMat(Sink.seq(), Keep.right())
.run(testKit.getMaterializer())
.toCompletableFuture()
.get();