My Weird Prompts
What Really Runs When You Compact an Agent's Context
21:30
Agent harnesses rely heavily on context compaction, but dedicated models built specifically for the task barely exist. Commercial tools like Claude Code and OpenAI use main models with built-in prompts or opaque server-side endpoints. Meanwhile, purpose-built open-source fine-tunes, token pruners like LLMLingua-2, and exotic latent compressors face practical trade-offs. Examining context…