Estimate tokens in a string or chat-message array. Fast, dependency-free, within ~10-20% of true tokenizer counts on English prose. Pass a model name to pick the right per-family estimator (openai, anthropic, google, llama, default).

Drop messages from the input array until the total is under maxTokens. Three strategies: drop-oldest (default), drop-middle, priority (uses each message's priority field). Always returns a structured result with token counts before and after; never throws across the wire.

List the built-in estimator families this server knows about. Useful for picking a model alias when the exact model name isn't recognized.