async tools support

[pgrayy]

Description

Support async tool definitions.

Related Issues

#83

Documentation PR

Will be following up on this.

Type of Change

• Bug fix
• New feature
• Breaking change
• Documentation update
• Other (please describe):

Testing

How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli

• I ran hatch run prepare
• Wrote new unit tests.
• Ran the integ tests.
• Ran the following test script:

@strands.tool
async def math_agent(exp: str):
    model = OpenAIModel({"api_key": "****"}, model_id="gpt-4o")
    agent = Agent(model=model, callback_handler=None)
    prompt = f"What is {exp}? Think through the steps."
    result = await agent.invoke_async(prompt)
    return result.message


model = OpenAIModel({"api_key": "****"}, model_id="gpt-4o")
agent = Agent(model=model, tools=[math_agent], callback_handler=None)
result = agent("Can you run the math_agent tool 4 times to help me with the calculation '2+2'? I want different perspectives")
print(result.message)

The tool is executed 4 times concurrently. Note, we are using Agent.__call__ which is synchronous itself but under the hood it creates an async event loop.

Checklist

• I have read the CONTRIBUTING document
• I have added any necessary tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
• My changes generate no new warnings
• Any dependent changes have been merged and published

---

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.