Anthropic Sonnet has trouble with dict result type

[jlowin]

Description

Reported in Slack - Sonnet repeatedly stumbles with return_type=dict. https://prefect-community.slack.com/archives/C079VLLH5D3/p1731491267965619

Example Code

import controlflow as cf

@cf.flow
def gen_mock_data(goal: str):
    agent_data = cf.Agent(
        name = "Website data structure generator",
        instructions = """You are a data structure expert. Your task is to generate realistic mock data for a website. You can directly return final result data in tool call without any other comments.""",
        
        model = 'anthropic/claude-3-5-sonnet-20240620',
    )
    mock_data_task = cf.Task(
        objective=f"""
        Please follow these guidelines:
    1. Include all necessary fields and relationships between data entities
    2. Generate a reasonable amount of sample data (10-20 items per category)
    3. Maintain data consistency across related entities
    4. Use realistic values for:
    - Names, titles, descriptions
    - Dates and timestamps
    - IDs and reference keys
    - Numeric values and statistics
    5. Follow these data quality rules:
    - No null values unless explicitly requested
    - Proper data types for each field
    - Consistent formatting for dates and special fields
    - Realistic data ranges and distributions
        Generate mock data for the goal: {goal}""",
        result_type=dict,
    #  completion_tools=[],
        agents=[agent_data],
    )
    json_data = mock_data_task.run(
        max_agent_turns=3,
        max_llm_calls=3,
    )
    print("Mock data:", json_data)
gen_mock_data("Generate a blog site mock data")

Version Information

ControlFlow version: 0.11.3.dev19+g0b0c9fb
       Prefect version: 3.1.0
LangChain Core version: 0.3.15
        Python version: 3.12.2
              Platform: macOS-15.1-arm64-arm-64bit
                  Path: /Users/jlowin/Developer/controlflow

Additional Context

No response