एजेंट्स के लिए कॉस्ट, लेटेन्सी और रिलायबिलिटी

import random, time

class BudgetExceeded(Exception):
    pass

class Budget:
    def __init__(self, max_tokens: int):
        self.max_tokens, self.used = max_tokens, 0
    def spend(self, tokens: int):
        self.used += tokens
        if self.used > self.max_tokens:
            raise BudgetExceeded("used " + str(self.used) + " tokens")

def call_model(prompt: str, timeout: float) -> tuple:
    # Placeholder: call your provider with this timeout.
    # Returns (text, tokens_used). Here it sometimes fails, for the demo.
    if random.random() < 0.3:
        raise TimeoutError("model did not answer in time")
    return "ok: " + prompt[:30], 500

def reliable_call(prompt: str, budget: Budget, tries: int = 3) -> str:
    for attempt in range(tries):
        try:
            text, tokens = call_model(prompt, timeout=30)
            budget.spend(tokens)
            return text
        except TimeoutError:
            wait = (2 ** attempt) + random.random()   # backoff with jitter
            time.sleep(wait * 0.01)                    # shortened for the demo
    return "FALLBACK: could not reach the model; handing over to a person."

budget = Budget(max_tokens=5000)
try:
    for step in range(20):
        print(step, reliable_call("step " + str(step), budget))
except BudgetExceeded as err:
    print("Stopped:", err)