モデルルーティング：すべてに1つのモデルを使うことをやめよう

ROUTING_RULES = {
    "classify": {"model": "qwen3-1.7B", "max_tokens": 100},
    "summarize": {"model": "qwen3-8B", "max_tokens": 500},
    "code_review": {"model": "qwen2.5-coder-7b", "max_tokens": 2000},
    "reason": {"model": "qwen3-32b", "max_tokens": 4000},
    "creative": {"model": "claude-sonnet-4", "max_tokens": 8000},
}

def route_request(task_type: str) -> dict:
    return ROUTING_RULES.get(task_type, ROUTING_RULES["reason"])

class CostAwareRouter:
    def __init__(self, budget_per_session: float = 0.10):
        self.budget = budget_per_session
        self.spent = 0.0
        self.models = {
            "cheap": {"model": "qwen3-8B", "cost": 0.0},
            "medium": {"model": "qwen3-32b", "cost": 0.0},
            "expensive": {"model": "claude-sonnet-4", "cost": 0.000015},
        }

    def route(self, task: str) -> str:
        ratio = self.spent / self.budget
        if ratio < 0.5:
            return self.models["expensive"]["model"]
        elif ratio < 0.8:
            return self.models["medium"]["model"]
        return self.models["cheap"]["model"]

class LatencyAwareRouter:
    def __init__(self):
        self.model_latencies = {
            "qwen3-1.7b": {"first_token": 0.05, "complete": 0.5},
            "qwen3-8B": {"first_token": 0.15, "complete": 2.0},
            "qwen3-32b": {"first_token": 0.5, "complete": 10.0},
            "claude-sonnet-4": {"first_token": 0.3, "complete": 5.0},
        }

    def route(self, target_latency: float) -> str:
        for model, latencies in sorted(
            self.model_latencies.items(),
            key=lambda x: x[1]["complete"]
        ):
            if latencies["complete"] <= target_latency:
                return model
        return "qwen3-1.7b"

class FallbackRouter:
    def __init__(self):
        self.fallback_chain = [
            {"model": "claude-sonnet-4", "timeout": 30},
            {"model": "qwen2.5-72b", "timeout": 60},
            {"model": "qwen3-32b", "timeout": 120},
            {"model": "qwen3-8b", "timeout": 300},
        ]

    def route_with_fallback(self, prompt: str) -> str:
        for config in self.fallback_chain:
            try:
                return self.call_model(
                    config["model"], prompt,
                    timeout=config["timeout"]
                )
            except (TimeoutError, APIError) as e:
                log.warning(f"Model {config['model']} failed: {e}")
                continue
        raise RuntimeError("All fallback models failed")