后训练协同与 Computer Use

def reward(task_ok, evidence_ok, seconds, cost, invalid_action):
    if invalid_action:
        return -10.0
    if not task_ok or not evidence_ok:
        return -2.0
    return 1.0 - 0.001 * seconds - 0.01 * cost

观察当前页面/截图 → 决定动作 → 执行动作 → 重新观察 → 判断目标是否满足

class FakeApp:
    def __init__(self):
        self.state = {"filters_open": False, "query": ""}

    def observe(self):
        return dict(self.state)

    def act(self, action):
        if action == "open_filters":
            self.state["filters_open"] = True
        elif action == "type_penguin" and self.state["filters_open"]:
            self.state["query"] = "penguin"
        else:
            raise ValueError("action not valid in current state")

app = FakeApp()
for step in range(5):
    observation = app.observe()
    if observation["filters_open"] and observation["query"] == "penguin":
        print("verified:", observation)
        break
    action = "open_filters" if not observation["filters_open"] else "type_penguin"
    app.act(action)
else:
    raise RuntimeError("task not completed within action budget")
assert app.observe() == {"filters_open": True, "query": "penguin"}

next_input = [{
    "type": "computer_call_output",
    "call_id": actual_computer_call_id,
    "output": {
        "type": "computer_screenshot",
        "image_url": "data:image/png;base64," + screenshot_base64,
    },
}]