​
Returns

It returns a result object from the Conversation Simulator containing the complete conversation history, status, and metadata. This is used to analyze how your agent performed in the test scenario. In order to run the simulation you need to use Galtea’s Agent. This agent manages your conversations with our simulation service so you don’t have to worry about it.

​
Example

import galtea

# Define your agent
class MyAgent(galtea.Agent):
    def call(self, input_data: galtea.AgentInput) -> galtea.AgentResponse:
        user_message = input_data.last_user_message_str()
        return galtea.AgentResponse(role="assistant", content=f"Echo: {user_message}")

# Create a session and run the simulation
session = galtea.sessions.create(version_id="your_version_id")
result = galtea.simulator.simulate(
    session_id=session.id,
    agent=MyAgent(),
    max_turns=5,
    log_inference_results=True,
    enable_last_inference=True,
    include_metadata=True
)

print(result.total_turns)
for message in result.messages:
    print(message.role, message.content)

​
Parameters

​
session_id
str
required
The session identifier for this simulation.
​
agent
Agent
required
Your implementation of the Agent class, containing your conversational logic.
​
max_turns
int
Maximum number of conversation turns. Default: 20
​
log_inference_results
bool
Whether to log inference results to the platform. Default: True
​
enable_last_inference
bool
Whether to call your agent one final time after the simulated user sends their last message. Default: True. When enabled, your agent will have the opportunity to respond to the conversation’s final user message, ensuring complete dialogue coverage for evaluation purposes.
​
include_metadata
bool
Whether to include metadata in the simulation result. Default: False