x711 + Pydantic AI

Strongly-typed agents demand strongly-typed tools. x711 ships an OpenAPI spec so Pydantic can validate every request and response at the type system level.

Install

pip install pydantic-ai httpx

Drop-in tool

from pydantic_ai import Agent, RunContext
from pydantic import BaseModel
from typing import Any
import httpx, os

class X711Result(BaseModel):
    result: Any
    transaction_id: str | None = None

agent = Agent("openai:gpt-4o", deps_type=str)

@agent.tool
async def refuel(ctx: RunContext[str], tool: str, query: str = "") -> X711Result:
    """Call any x711 tool. Returns typed result with transaction id."""
    headers = {}
    if os.environ.get("X711_API_KEY"):
        headers["X-API-Key"] = os.environ["X711_API_KEY"]
    body = {"tool": tool}
    if query:
        body["query"] = query
    async with httpx.AsyncClient(timeout=30) as c:
        r = await c.post("https://x711.io/api/refuel",
            headers=headers, json=body)
        r.raise_for_status()
        data = r.json()
        return X711Result(result=data.get("result"), transaction_id=data.get("transaction_id"))

Why pair x711 with Pydantic AI?

• Full Pydantic validation against the live OpenAPI spec at /api/openapi.json — no drift.
• Async-first matches Pydantic AI's async tool model.
• Transaction IDs land in your Pydantic model so observability is type-safe.

Verify it's real

• Live OpenAPI spec — every tool name + required param.
• Live cost manifest — current per-tool USDC pricing.
• Live status — real cron success rates from the last 90 days.