KPI-Weighted Routing

import cascadeflow

cascadeflow.init(mode="enforce")

with cascadeflow.run(
    budget=2.00,
    kpi_weights={"quality": 0.8, "cost": 0.1, "latency": 0.1},
    kpi_targets={"quality": 0.9}
) as session:
    # Routes to highest-quality models within budget
    result = await agent.run("Draft a legal contract clause")
    print(session.summary())

with cascadeflow.run(
    budget=5.00,
    kpi_weights={"cost": 0.7, "quality": 0.2, "latency": 0.1}
) as session:
    # Routes to cheapest models that meet quality floor
    for query in batch_queries:
        result = await agent.run(query)
    print(f"Total cost: ${session.summary()['cost_total']:.4f}")

with cascadeflow.run(
    kpi_weights={"latency": 0.7, "quality": 0.2, "cost": 0.1},
    max_latency_ms=2000.0
) as session:
    # Routes to fastest models, hard cap at 2 seconds
    result = await agent.run("Quick classification task")

with cascadeflow.run(
    kpi_weights={"quality": 0.4, "energy": 0.3, "cost": 0.3},
    max_energy=100.0
) as session:
    # Balances quality with energy efficiency
    result = await agent.run("Summarize this report")
    print(f"Energy used: {session.summary()['energy_used']:.1f} units")

@cascadeflow.agent(
    budget=0.10,
    kpi_weights={"cost": 0.9, "quality": 0.1}
)
async def triage_agent(query: str):
    """Quick classification — prioritize cost."""
    return await llm.complete(query)

@cascadeflow.agent(
    budget=2.00,
    kpi_weights={"quality": 0.9, "cost": 0.1},
    kpi_targets={"quality": 0.95}
)
async def analysis_agent(query: str):
    """Deep analysis — prioritize quality."""
    return await llm.complete(query)