Skip to main content

​
Test Mode

Test mode lets you interact with your voice agent in the terminal using pure text — no phone calls, no STT/TTS, no external services required. It simulates a phone conversation for rapid agent development.

​
Quick Start

import asyncio
from patter import Patter

phone = Patter(openai_key="sk-...", mode="local")

agent = phone.agent(
    system_prompt="You are a helpful customer service agent for Acme Corp.",
    first_message="Hello! Welcome to Acme Corp. How can I help you today?",
)

asyncio.run(phone.test(agent))
This opens an interactive REPL: 
============================================================
  PATTER TEST MODE
============================================================
  Agent: gpt-4o-realtime / alloy
  Provider: openai_realtime
  Call ID: test_a1b2c3d4e5f6
  Caller: +15550000001  →  Callee: +15550000002
------------------------------------------------------------
  Commands: /quit  /transfer <number>  /hangup  /history
============================================================

  Agent: Hello! Welcome to Acme Corp. How can I help you today?

  You: I need to return an item
  Agent: I'd be happy to help with your return...

​
Commands

CommandDescription
/quitEnd the test session.
/hangupSimulate hanging up the call.
/transfer <number>Simulate a call transfer.
/historyPrint the full conversation history.

​
Using with on_message

Test mode works with custom message handlers, exactly as they would work in production: 
async def on_message(data, call_control):
    user_text = data["text"]
    history = data["history"]

    if "cancel" in user_text.lower():
        await call_control.transfer("+15550001111")
        return "Let me transfer you to our cancellation team."

    return f"You said: {user_text}"

asyncio.run(phone.test(agent, on_message=on_message))
The call_control parameter is automatically injected if your handler accepts two arguments.

​
Using with Built-in LLM Loop

When no on_message handler is provided and an openai_key is available, test mode uses the built-in LLM loop with streaming responses: 
agent = phone.agent(
    system_prompt="You are a restaurant booking assistant.",
    tools=[
        {
            "name": "check_availability",
            "description": "Check table availability",
            "parameters": {
                "type": "object",
                "properties": {
                    "date": {"type": "string"},
                    "party_size": {"type": "integer"},
                },
            },
            "webhook": "https://api.example.com/availability",
        }
    ],
)

asyncio.run(phone.test(agent))
The LLM loop supports tool calling — tools are executed via their configured webhooks just like in production.

​
Event Callbacks

Test mode fires the same lifecycle callbacks as serve(): 
async def on_call_start(event):
    print(f"Test call started: {event['call_id']}")
    # Return overrides if needed
    return {"variables": {"customer_name": "Test User"}}

async def on_call_end(event):
    print(f"Test call ended: {event['call_id']}")
    print(f"Transcript: {len(event['transcript'])} messages")

asyncio.run(phone.test(
    agent,
    on_call_start=on_call_start,
    on_call_end=on_call_end,
))
Test mode is designed for development only. It does not use any external APIs (except OpenAI for the LLM loop when no on_message is provided).