탐색 중:

planetaryescape

Backend budget tracking patterns for AI generation. Awareness-based tracking (not blocking), tool timeouts, per-tool rate limits, token estimates, context window management, truncation strategies, search quality detection. Triggers on budget, tool timeout, rate limit, token estimate, truncation, context window, search quality, diminishing returns.

affaan-m

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.