Skip to content

complexity

diapason.learning.routing.complexity

Query complexity analyzer — scores queries and suggests token budgets.

Produces a numeric complexity score (0.0–1.0) and a suggested max_tokens budget based on query characteristics such as length, domain signals (code, math, multi-step reasoning), and whether the target model is a thinking model that needs extra headroom.

ComplexityQueryAnalyzer

Bases: QueryAnalyzer

Query analyzer that produces a complexity-aware RoutingContext.

Drop-in replacement for DefaultQueryAnalyzer — adds complexity_score, has_reasoning, and suggested_max_tokens to the returned RoutingContext.

ComplexityResult dataclass

Output of the complexity analysis.

adjust_tokens_for_model(suggested, model_name=None)

Multiply the token budget when the target is a thinking model.

is_thinking_model(model_name)

Return True if the model is known to use internal chain-of-thought.

score_complexity(query)

Score a query's complexity from 0.0 (trivial) to 1.0 (very complex).

The score is a weighted combination of independent signals, each contributing a fraction between 0 and 1. Weights reflect how much each signal correlates with the amount of reasoning and output tokens a model will need.