在 ADK 里评测实时语音智能体

from google.adk.agents.llm_agent import Agent
from google.adk.tools.tool_context import ToolContext
from google.adk.workflow import START, Workflow
from pydantic import BaseModel, Field


LIVE_MODEL = "gemini-live-2.5-flash-native-audio"




def validate_date_of_birth(dob: str, tool_context: ToolContext) -> dict:
  """Validate a confirmed date of birth against records (mocked)."""
  match = dob == "1985-07-12"
  tool_context.state["dob_verified"] = match
  return {"match": match}




greeter_agent = Agent(
    model=LIVE_MODEL,
    name="greeter_agent",
    mode="task",
    instruction="You are Sam, a friendly care-team assistant. Greet the caller "
    "and confirm you're speaking with John Doe before sharing anything else. "
    "Ask one question per turn, then complete your task with the confirmed name.",
)


dob_verifier_agent = Agent(
    model=LIVE_MODEL,
    name="dob_verifier_agent",
    mode="task",
    tools=[validate_date_of_birth],
    instruction="Ask for the caller's date of birth, read it back to confirm, "
    "then call validate_date_of_birth in YYYY-MM-DD format. Complete your task "
    "with 'verified' or 'unverified'.",
)


goals_agent = Agent(
    model=LIVE_MODEL,
    name="goals_agent",
    mode="task",
    instruction="Identity is verified. Proactively share the upcoming "
    "appointment on Tuesday, June 16th at 3 PM with Dr. Example, answer any "
    'questions, then wrap up warmly and end with "Goodbye."',
)


root_agent = Workflow(
    name="live_workflow",
    edges=[
        (START, greeter_agent),
        (greeter_agent, dob_verifier_agent),
        (dob_verifier_agent, goals_agent),
    ],
)

{
  "eval_id": "example_scenario_case",
  "conversation_scenario": {
    "starting_prompt": "Hello?",
    "conversation_plan": "You are John Doe. Confirm your name when greeted. When asked for your date of birth, give July 12th, 1985, and confirm it when read back. Listen to the appointment details, ask what you should bring to the visit, then say you have no other questions and let the call wrap up.",
    "user_persona": "NOVICE"
  },
  "session_input": {
    "app_name": "live_workflow",
    "user_id": "test_user_id",
    "state": {}
  }
}

{
  "eval_id": "example_fixed_case",
  "conversation": [
    {
      "user_content": {
        "role": "user",
        "parts": [{ "text": "Hi, yes, this is John Doe." }]
      }
    },
    {
      "user_content": {
        "role": "user",
        "parts": [{ "text": "My date of birth is July 12th, 1985." }]
      }
    }
  ]
}

{
  "criteria": {
    "rubric_based_multi_turn_trajectory_quality_v1": {
      "threshold": 0.7,
      "judge_model_options": { "judge_model": "gemini-3.7-flash" },
      "rubrics": [
        {
          "rubric_id": "verifies_identity_first",
          "rubric_content": {
            "text_property": "Across the call, the agent confirms the caller's name and validates their date of birth before disclosing any appointment details."
          }
        }
      ]
    }
  },
  "live_model_config": {
    "timeout_seconds": 300
  },
  "user_simulator_config": {
    "type": "llm_audio",
    "model": "gemini-3.7-flash",
    "max_allowed_invocations": 10,
    "audio_model": "gemini-3.1-flash-tts-preview",
    "audio_model_configuration": {
      "response_modalities": ["AUDIO"],
      "speech_config": {
        "voice_config": {
          "prebuilt_voice_config": { "voice_name": "Kore" }
        },
        "language_code": "en-US"
      }
    }
  }
}

uv run adk eval \
  contributing/samples/live/live_workflow \
  contributing/samples/live/live_workflow/live_workflow.evalset.json \
  --config_file_path contributing/samples/live/live_workflow/test_config.json