Config Agent Deployment issue.

[aherzberg-go]

Describe the Bug:
Deploying default config agents to Agent Engine is successful. Adding any tool to the config agent results in deployment failures.

Steps to Reproduce:
Create a new config agent:
adk create --type=config new_agent

Run: adk deploy agent_engine .... new_agent

-> successful

add any tool to root_agent.yaml:

name: new_agent
model: gemini-2.5-flash
agent_class: LlmAgent
instruction: You are the root agent that coordinates other agents.
sub_agents: []
tools:
  - name: new_agent.get_weather

add custom tool to __init__.py

def get_weather(city: str, unit: str):
    """
    Retrieves the weather for a city in the specified unit.

    Args:
        city (str): The city name.
        unit (str): The temperature unit, either 'Celsius' or 'Fahrenheit'.
    """
    # ... function logic ...
    return {"status": "success", "report": f"Weather for {city} is sunny."}

Test the agent in adk web -> it works

Run: adk deploy agent_engine .... new_agent

it fails

Expected Behavior:
Succesfull deploy.

Observed Behavior:

Environment Details:

• ADK Library Version: 1.26.0
• Desktop OS:** macOS
• Python Version Python 3.14.3:

Model Information:

• Are you using LiteLLM: No
• Which model is being used: gemini-2.5-pro / gemini-2.5-flash

---

🟡 Optional Information

Additional Context:
Also the adk config example: multi_agent_llm_config
doesnt work.

Any other configuration, via tools.py etc. didn't work as well
How often has this issue occurred?:

• Always (100%)

[sanketpatil06]

Hi @aherzberg-go, To deploy agent on Agent Engine, you could try define your agent in python file and then try to deploy that on Agent Engine. You could follow deployment section in ADK documentation, this step by step information on this topic.
If you still face this issue feel free to reach out.