An Empirical Cost Attribution of Context-Compression Gateways in Multi-Turn Coding Agents

Excerpt

arXiv:2609.22114v1 Announce Type: new Abstract: Context compression is widely proposed as a way to cut the token bill of LLM coding agents, and public benchmarks report that aggressive compression preserves task-solving quality. These two facts do not imply the third one commonly assumed: that compressing file reads saves money in a real multi-turn agent. We instrument a production compression gateway (Paritok) between coding agents (Claude Code, Codex) and frontier LLMs (Claude Sonnet, GPT-5),