Skip to content

Warmup requests seems to waste tokens #445

@bonadio

Description

@bonadio

Hi, when I run this simple example

import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions

async def main():
    async for message in query(
        prompt="What files are in the current directory?",
        options=ClaudeAgentOptions(allowed_tools=["Bash", "Glob"])
    ):
        if hasattr(message, "result"):
            print(message.result)

asyncio.run(main())

I see 2 network request: 1 for Haiku and 1 for Sonnet with user content Warmup. This seems to just waste tokens.

Why is that needed?

Thanks

Metadata

Metadata

Assignees

No one assigned

    Labels

    questionFurther information is requested

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions