httppayai

agents.writerslogic.com

Chooses which context items an agent should put into a prompt without exceeding a token budget: every mandatory item and everything it depends on is always included, then optional items by descending priority (each with the dependencies it pulls in) while they fit. Token counts come from the caller or from o200k_base / cl100k_base; any other tokenizer name returns unsupported (there is no Claude tokenizer, so nothing is estimated). Greedy by priority, not an optimal knapsack; per-item counts are summed and do not model merges across item boundaries (use perItemOverhead for separators). Does not summarize or rewrite items.