0.2.2

What's Changed

• feat: Support reasoning for 3.7 by @Wh1isper in #15

in this way:

def get_random_number():
    """
    Return a random number using the randint
    """
    res = str(randint(0, 100))
    print("Tool Called with result: ", res)
    return res

agent = Agent(
    BedrockModel(model_name="us.anthropic.claude-3-7-sonnet-20250219-v1:0"),
    system_prompt="Return a random number using your tools",
    tools=[get_random_number],
    model_settings={
        "enable_reasoning": True,
        # "budget_tokens": "1024",
    }
)

I'm looking forward to everyone's experience, I'll try to fix possible issues quickly!

Full Changelog: 0.2.1...0.2.2

0.2.1

What's Changed

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in #14

Full Changelog: 0.2.0...0.2.1

0.2.0

What's Changed

• fix: empty tool call args by @Wh1isper in #13

Full Changelog: 0.1.9...0.2.0

0.1.9

What's Changed

• Add missing property decorator by @richin13 in #11

New Contributors

• @richin13 made their first contribution in #11

Full Changelog: 0.1.8...0.1.9

0.1.8

Full Changelog: 0.1.7...0.1.8

0.1.7

Full Changelog: 0.1.6...0.1.7

0.1.6

What's Changed

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in #8
• feat: Upver pydantic-ai to 0.0.24 by @Wh1isper in #9

Full Changelog: 0.1.5...0.1.6

0.1.5

What's Changed

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in #6
• feat: Drop agent model by @Wh1isper in #7

Full Changelog: 0.1.4...0.1.5

0.1.4

What's Changed

• feat: Support pydantic 0.0.21 by @Wh1isper in #5

Full Changelog: 0.1.3...0.1.4

0.1.3

Full Changelog: 0.1.2...0.1.3