Rules

# never route to small models when the conversation is long
Rule(if_context_tokens_gt=4000, deny_tiers=["small"])

# never route to small or medium when cost is a concern
Rule(if_estimated_cost_gt=0.05, deny_tiers=["small", "medium"])

# always use the best model for sensitive tasks
Rule(if_task="legal-review", pin_tier="large")
Rule(if_task="medical-advice", pin_tier="large")

# prefer cheap models when cost is low
Rule(prefer_tier="small", if_estimated_cost_gt=0.001)

Rule(if_error_code=429, escalate=True)   # rate limit → try next tier
Rule(if_error_code=529, escalate=True)   # overloaded → try next tier