OpenAI Agents SDK アプリで CAPTCHA を解決する

# pip install capsolver-agent openai-agents
# export CAPSOLVER_API_KEY=CAP-XXXXXX
# export OPENAI_API_KEY=sk-XXXXXX

import json
import os
from agents import Agent, Runner, function_tool, set_default_openai_api, set_tracing_disabled
from capsolver_agent.schema import create_executor
from _env import load_example_env  # demo only: reads repo-root .env

load_example_env()
set_tracing_disabled(True)
if os.environ.get("OPENAI_BASE_URL"):  # OpenAI-compatible gateway (DeepSeek, ...)
    set_default_openai_api("chat_completions")

executor = create_executor()  # wraps a capsolver-core engine; key from CAPSOLVER_API_KEY

@function_tool
async def solve_captcha(
    captcha_type: str,
    website_url: str,
    website_key: str,
    proxy: str | None = None,   # pass a proxy for proxy-bound challenges
) -> str:
    """Solve a captcha (reCaptchaV2 / reCaptchaV3 / cloudflare) and return the result as JSON.

    Call this whenever a page blocks the task with a CAPTCHA. Provide the
    captcha type, the page URL, and the site key from the challenge widget.
    """
    args = {"captcha_type": captcha_type, "website_url": website_url, "website_key": website_key}
    if proxy:
        args["proxy"] = proxy
    result = await executor.execute("solve_captcha", args)
    return json.dumps(result, ensure_ascii=False)

agent = Agent(
    name="captcha-agent",
    model=os.environ.get("OPENAI_MODEL", "gpt-4o"),
    instructions=(
        "You complete web tasks. When a page shows a CAPTCHA, call solve_captcha "
        "with the captcha type, page URL and site key, then continue."
    ),
    tools=[solve_captcha],
)

result = Runner.run_sync(
    agent,
    "Solve the reCaptchaV2 at https://www.google.com/recaptcha/api2/demo with site key "
    "6Le-wvkSAAAAAPBMRTvw0Q4Muexq9bi0DJwx_mJ- and report the first 40 characters of the token.",
)
print(result.final_output)